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

    Neuronpedia

    INDEX
    Explanations

    A, old, Basic, Bi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    0.45
     неболь
    0.44
     Когда
    0.44
    losti
    0.44
    жнему
    0.44
    <unused262>
    0.43
    Firm
    0.43
     Более
    0.43
    ленный
    0.42
    ленным
    0.42
    POSITIVE LOGITS
     ranged
    0.55
    مل
    0.54
    سر
    0.54
     right
    0.53
     all
    0.47
     bookings
    0.46
     baton
    0.46
    ரா
    0.45
     woman
    0.44
     confirmed
    0.44
    Act Density 0.003%

    No Known Activations