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

    Neuronpedia

    INDEX
    Explanations

    exception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (img
    -0.07
     li
    -0.06
    쳐
    -0.06
    beans
    -0.06
     τ
    -0.06
     Raq
    -0.06
    loi
    -0.06
    тоф
    -0.06
    _styles
    -0.06
    ázd
    -0.06
    POSITIVE LOGITS
    .unsubscribe
    0.07
     longstanding
    0.06
    aro
    0.06
    imer
    0.06
     excellent
    0.06
     Conor
    0.06
    「
    0.06
    far
    0.06
    _DISABLED
    0.06
     зовніш
    0.06
    Act Density 0.004%

    No Known Activations