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

    Neuronpedia

    INDEX
    Explanations

    shark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     command
    -0.06
    ocide
    -0.06
     troubling
    -0.06
     Feeling
    -0.06
    TEMPLATE
    -0.06
     六
    -0.06
    _statement
    -0.06
     Bris
    -0.06
    織
    -0.05
    دی
    -0.05
    POSITIVE LOGITS
     youngsters
    0.08
     Sharks
    0.07
    жно
    0.07
    ={},
    0.06
     sharks
    0.06
    ertainment
    0.06
     $__
    0.06
    >"↵
    0.06
    /how
    0.06
    alon
    0.06
    Act Density 0.007%

    No Known Activations