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

    Neuronpedia

    INDEX
    Explanations

    Specific scenarios/quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bootstrap
    -0.07
    กรณ
    -0.06
     try
    -0.06
    lio
    -0.06
     каль
    -0.06
     інш
    -0.06
    Cheap
    -0.06
     fears
    -0.06
    幅
    -0.06
     vtx
    -0.06
    POSITIVE LOGITS
    []}
    0.06
    .requires
    0.06
    arde
    0.06
    YD
    0.06
    íme
    0.06
    opening
    0.06
    ograd
    0.06
    alten
    0.06
     annonce
    0.06
    (sound
    0.06
    Act Density 0.000%

    No Known Activations