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

    Neuronpedia

    INDEX
    Explanations

    where/which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DEALINGS
    -0.06
     ob
    -0.06
     seeming
    -0.06
     обязательно
    -0.06
     piercing
    -0.06
     Annual
    -0.06
    ими
    -0.06
    orio
    -0.06
     twisted
    -0.06
    (Sub
    -0.05
    POSITIVE LOGITS
    産
    0.08
    =-=-=-=-=-=-=-=-
    0.06
     hit
    0.06
    avascript
    0.06
    腐
    0.06
     thaw
    0.06
    _collision
    0.06
     karşılık
    0.06
    養
    0.06
    เ�
    0.06
    Act Density 0.027%

    No Known Activations