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
    稔
    -0.08
    .presenter
    -0.07
    @implementation
    -0.07
    😻
    -0.07
    (binding
    -0.07
    ercise
    -0.07
    健
    -0.07
    ident
    -0.06
    indsay
    -0.06
     strncmp
    -0.06
    POSITIVE LOGITS
     imply
    0.08
    jej
    0.07
     probabilities
    0.07
    .Face
    0.07
    唛
    0.07
    räg
    0.07
    种种
    0.07
     Furthermore
    0.07
    оказ
    0.07
    ened
    0.07
    Act Density 0.002%

    No Known Activations