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

    Neuronpedia

    INDEX
    Explanations

    feeling good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .launch
    -0.06
    歩
    -0.06
     allem
    -0.06
     Preservation
    -0.06
     Signing
    -0.06
    ルド
    -0.06
    AV
    -0.06
     Δη
    -0.06
    berman
    -0.06
    инг
    -0.06
    POSITIVE LOGITS
    Born
    0.07
     costumes
    0.06
     익
    0.06
     feels
    0.06
     hence
    0.06
    (contact
    0.06
    (front
    0.06
    pageSize
    0.06
    xDB
    0.06
    .,↵
    0.06
    Act Density 0.010%

    No Known Activations