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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Door
    -0.07
     Door
    -0.07
     Midwest
    -0.06
    Screen
    -0.06
     reaching
    -0.06
    756
    -0.06
    елик
    -0.06
     Alternative
    -0.06
    Io
    -0.06
     Raymond
    -0.06
    POSITIVE LOGITS
    DidAppear
    0.07
    BOOLE
    0.06
     зай
    0.06
     descendant
    0.06
    Interested
    0.06
    /light
    0.06
     minOccurs
    0.06
     hil
    0.06
    /apt
    0.06
     :/
    0.06
    Act Density 0.153%

    No Known Activations