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

    Neuronpedia

    INDEX
    Explanations

    log

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Operations
    -0.07
     Stunning
    -0.07
    _Config
    -0.07
    анных
    -0.07
     roz
    -0.07
    çok
    -0.06
    contro
    -0.06
    Oops
    -0.06
    hev
    -0.06
    ivatel
    -0.06
    POSITIVE LOGITS
    udded
    0.06
     seeming
    0.06
     lowercase
    0.06
    _il
    0.06
     ull
    0.06
    irk
    0.06
    QUENCE
    0.06
     mere
    0.06
     tranquil
    0.06
     campground
    0.06
    Act Density 0.005%

    No Known Activations