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

    Neuronpedia

    INDEX
    Explanations

    susceptibilities depression increase Justin Curly maple Early Recurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roboc
    -0.73
     keadaan
    -0.69
     glaubt
    -0.67
    gin
    -0.66
     Tort
    -0.66
    ᆨ
    -0.65
     situated
    -0.65
     commutation
    -0.64
     representatives
    -0.63
     penderita
    -0.63
    POSITIVE LOGITS
     dia
    1.09
     susceptibility
    0.99
     Dia
    0.94
     froze
    0.93
    Dia
    0.89
    0.88
     freeze
    0.82
    мом
    0.77
     Dias
    0.75
    橢
    0.75
    Act Density 0.025%

    No Known Activations