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

    Neuronpedia

    INDEX
    Explanations

    specific areas following 'of'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atletas
    0.77
     lontano
    0.77
     방식으로
    0.74
     المسافه
    0.74
     چیز
    0.73
     manière
    0.73
     quantidade
    0.72
     cantidad
    0.72
    newEvent
    0.71
    ױ
    0.71
    POSITIVE LOGITS
     discussion
    1.03
     concern
    1.01
     study
    0.99
     overlap
    0.98
     disbursement
    0.97
     наиболь
    0.93
     dispute
    0.92
     contention
    0.88
     interest
    0.87
     Interest
    0.86
    Act Density 0.110%

    No Known Activations