Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to discovering or accessing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after commas or common verbs

    np_acts-logits-general · gemini-2.0-flash

    find/found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.69
     betweenstory
    -0.69
     <<<<<<<<<<<<<<
    -0.68
    StoreMessageInfo
    -0.56
    adaptiveStyles
    -0.52
     يتيمه
    -0.52
     Vikipedi
    -0.50
    AnimationsModule
    -0.48
    Huy
    -0.46
    writeFieldEnd
    -0.46
    POSITIVE LOGITS
     found
    1.33
    found
    1.08
     Found
    1.04
     finden
    1.01
     findest
    0.98
     find
    0.98
    Found
    0.96
     finds
    0.93
     znajd
    0.92
     najdete
    0.92
    Act Density 0.316%

    No Known Activations