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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typically
    -0.07
    -system
    -0.07
     holds
    -0.07
     start
    -0.07
     thử
    -0.07
    -tests
    -0.06
     alcohol
    -0.06
     smugg
    -0.06
    _friend
    -0.06
     zag
    -0.06
    POSITIVE LOGITS
    ORITY
    0.06
     kaliteli
    0.06
    Й
    0.06
    СО
    0.06
    ILLISE
    0.06
    iv
    0.06
    (['/
    0.06
    ίκ
    0.06
     umění
    0.06
    .SingleOrDefault
    0.06
    Act Density 0.079%

    No Known Activations