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

    Neuronpedia

    INDEX
    Explanations

    Rukarara River, cerebrex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     able
    0.86
    ётся
    0.84
    ifier
    0.81
     devoid
    0.77
    ification
    0.77
     exactly
    0.76
     noc
    0.75
     attentive
    0.75
     allergies
    0.75
     sens
    0.75
    POSITIVE LOGITS
    ת
    1.12
    iidae
    1.01
    jų
    0.97
    uirre
    0.93
    坡
    0.91
    मीडिया
    0.88
    城堡
    0.88
    t
    0.87
    י
    0.86
    lung
    0.85
    Act Density 0.442%

    No Known Activations