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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     şarkı
    -0.07
     adına
    -0.07
     чувств
    -0.07
     Advisors
    -0.06
     alanda
    -0.06
     This
    -0.06
     tagName
    -0.06
    Expect
    -0.06
    _checksum
    -0.06
     lb
    -0.06
    POSITIVE LOGITS
    CLUDED
    0.07
    POCH
    0.06
    Workspace
    0.06
     ￥
    0.06
     explodes
    0.06
    (region
    0.06
     boredom
    0.06
     rnn
    0.06
     Nine
    0.06
    odos
    0.06
    Act Density 0.000%

    No Known Activations