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

    Neuronpedia

    INDEX
    Explanations

    as far as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    மிகு
    0.91
    ött
    0.88
     وغيرها
    0.84
    которые
    0.81
    ři
    0.80
     Quelles
    0.79
     وبين
    0.78
    esse
    0.77
     faites
    0.76
    ğinde
    0.75
    POSITIVE LOGITS
     goes
    1.20
     pertains
    1.20
     касается
    1.17
     concerned
    1.14
     practicable
    1.08
     regards
    1.04
     concerne
    1.04
     concerns
    1.02
     Applicable
    0.99
     knowledge
    0.98
    Act Density 0.003%

    No Known Activations