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

    Neuronpedia

    INDEX
    Explanations

    MTSamples BYD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contribu
    0.47
     configur
    0.42
    વેશ
    0.42
     libido
    0.40
     relações
    0.40
     Loads
    0.40
    ल्लाला
    0.40
    ｂ
    0.39
     Doesn
    0.39
    ካት
    0.39
    POSITIVE LOGITS
    ISTR
    0.56
    ك
    0.53
     NDR
    0.52
    HDR
    0.49
    change
    0.48
    hov
    0.47
     инстру
    0.47
     NSR
    0.47
    IDENTITY
    0.46
    Identity
    0.46
    Act Density 0.000%

    No Known Activations