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

    Neuronpedia

    INDEX
    Explanations

    likely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isbn
    -0.09
    zano
    -0.08
    atro
    -0.08
    ानम
    -0.07
    ダー
    -0.07
     Gör
    -0.07
    urope
    -0.07
     prostitu
    -0.07
     Macros
    -0.07
    ाओ
    -0.07
    POSITIVE LOGITS
     likely
    0.16
     Likely
    0.12
    likely
    0.10
     unlikely
    0.08
     Lik
    0.08
    Lik
    0.08
     likelihood
    0.08
     liable
    0.07
     akin
    0.06
    .lazy
    0.06
    Act Density 0.017%

    No Known Activations