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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe creating or establishing a space or identity

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

    carving or forging something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commit
    -0.42
     toxicity
    -0.38
    🏫
    -0.36
     administration
    -0.35
     receive
    -0.35
     received
    -0.34
     underwent
    -0.34
     BIBSYS
    -0.33
     boycott
    -0.33
     every
    -0.32
    POSITIVE LOGITS
     carve
    0.68
    carved
    0.65
     kasarigan
    0.61
    EndContext
    0.59
     intStringLen
    0.58
     propOrder
    0.57
     Numerade
    0.57
     Италијани
    0.56
    httphttps
    0.56
    Indented
    0.56
    Act Density 0.016%

    No Known Activations