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

    Neuronpedia

    INDEX
    Explanations

    meaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    узы
    -0.07
    bow
    -0.07
     behavioural
    -0.06
    (PRO
    -0.06
    Это
    -0.06
    plates
    -0.06
    (last
    -0.06
    enstein
    -0.06
    .header
    -0.06
    uploaded
    -0.06
    POSITIVE LOGITS
    osoph
    0.06
    .Void
    0.06
     sel
    0.06
    ुजर
    0.06
    ilt
    0.06
     úspěš
    0.06
     Оп
    0.06
    /modal
    0.06
     disgu
    0.06
     丶
    0.06
    Act Density 0.011%

    No Known Activations