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

    Neuronpedia

    INDEX
    Explanations

    connection string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onglet
    0.70
    CAB
    0.68
    text
    0.67
     Hé
    0.65
    Ş
    0.64
    Re
    0.64
    Př
    0.63
    leri
    0.63
     Kav
    0.63
    momentum
    0.62
    POSITIVE LOGITS
     handsets
    0.91
     telephones
    0.83
     conditionals
    0.81
     cordless
    0.80
     neutrophils
    0.79
     puppets
    0.77
     nozzles
    0.76
    де
    0.76
     phones
    0.76
    न्छ
    0.76
    Act Density 0.001%

    No Known Activations