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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิลล
    -0.06
    .Owner
    -0.06
     lx
    -0.06
     vanity
    -0.06
    280
    -0.06
     diffuse
    -0.06
    usa
    -0.06
    72
    -0.06
    love
    -0.06
     enlightenment
    -0.06
    POSITIVE LOGITS
    _native
    0.07
     Ducks
    0.07
    UIApplication
    0.07
    ionate
    0.06
     وقت
    0.06
     更
    0.06
    안
    0.06
    IDGET
    0.06
    ugged
    0.06
     squared
    0.06
    Act Density 0.020%

    No Known Activations