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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EqualityComparer
    -0.07
     <<
    -0.06
    .TAG
    -0.06
    osc
    -0.06
    asure
    -0.06
     �
    -0.06
    ателем
    -0.06
    hů
    -0.06
    igm
    -0.06
     META
    -0.06
    POSITIVE LOGITS
     prisoner
    0.07
     toch
    0.06
     knows
    0.06
     Nisan
    0.06
    Nich
    0.06
     protesting
    0.06
     managing
    0.06
     onslaught
    0.05
     paso
    0.05
    thal
    0.05
    Act Density 0.072%

    No Known Activations