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

    Neuronpedia

    INDEX
    Explanations

    address-related information or postal details

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

    after "user" or "<start_of_turn>user"

    np_acts-logits-general · gemini-2.0-flash

    postal academy letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.68
    awtextra
    -0.63
    fjspx
    -0.60
    jsxFileName
    -0.59
     rhestr
    -0.58
    ⟬
    -0.57
    brtc
    -0.55
     snippetHide
    -0.55
     <<<<<<<<<<<<<<
    -0.53
    endwhile
    -0.53
    POSITIVE LOGITS
    ViewFeatures
    0.40
     mail
    0.37
     Box
    0.33
     paquetes
    0.33
     box
    0.31
    Box
    0.30
    tovní
    0.30
     affairs
    0.29
     kautta
    0.29
     отделение
    0.29
    Act Density 0.069%

    No Known Activations