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

    Neuronpedia

    INDEX
    Explanations

    horses and ponies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Snail
    -0.82
     précieux
    -0.77
    Snail
    -0.76
    SIST
    -0.76
     snail
    -0.76
     Collie
    -0.74
    roaches
    -0.73
    wochen
    -0.73
     formant
    -0.73
     ident
    -0.73
    POSITIVE LOGITS
    𝚡
    0.90
     Keep
    0.87
    uples
    0.82
    wss
    0.81
     Qualitäts
    0.81
    celtic
    0.81
    ,:);
    0.81
     Mr
    0.80
     Major
    0.79
    +//
    0.79
    Act Density 0.010%

    No Known Activations