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
    _RESOURCES
    -0.07
     Sem
    -0.07
     lng
    -0.06
     Kore
    -0.06
     RESPONSE
    -0.06
    'est
    -0.06
     rows
    -0.06
    クロ
    -0.06
    Hint
    -0.06
    hill
    -0.06
    POSITIVE LOGITS
     xxx
    0.07
    选
    0.07
    /:
    0.06
     ██
    0.06
    .Char
    0.06
     physicists
    0.06
    Keith
    0.06
    	emit
    0.06
     fury
    0.06
     bitten
    0.06
    Act Density 0.001%

    No Known Activations