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

    Neuronpedia

    INDEX
    Explanations

    California

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Instruction
    -0.06
     cocktail
    -0.06
     Cricket
    -0.06
    SmartyHeaderCode
    -0.06
    operate
    -0.06
    -circle
    -0.06
    _pod
    -0.06
    advert
    -0.06
     कम
    -0.06
    tips
    -0.06
    POSITIVE LOGITS
     problemas
    0.07
    _flat
    0.07
     amazingly
    0.07
    BOOLE
    0.06
    real
    0.06
    лаб
    0.06
    ικός
    0.06
    -transparent
    0.06
    ерів
    0.06
    ้องก
    0.06
    Act Density 0.012%

    No Known Activations