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

    Neuronpedia

    INDEX
    Explanations

    describing procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arter
    -0.08
    brero
    -0.07
    meyi
    -0.07
    处
    -0.07
    idia
    -0.07
    manın
    -0.07
    crease
    -0.07
     �
    -0.07
    appro
    -0.07
    XPath
    -0.07
    POSITIVE LOGITS
    .PUT
    0.07
    โปร
    0.06
    ________________________________
    0.06
    UND
    0.06
     grieving
    0.06
    ..."↵
    0.06
    ONY
    0.06
    /****************************************************************
    0.06
    ();
↵
↵
↵
    0.05
     prioritize
    0.05
    Act Density 0.439%

    No Known Activations