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

    Neuronpedia

    INDEX
    Explanations

    care

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.58
    Predecesor
    -0.48
    ModelSerializer
    -0.47
    __(/*!
    -0.45
    outen
    -0.43
    MOUTH
    -0.41
    ANDUM
    -0.40
    Enciclopedia
    -0.40
    ностей
    -0.39
    quirer
    -0.39
    POSITIVE LOGITS
     costs
    0.70
     financières
    0.66
    costs
    0.63
     cost
    0.63
    Costs
    0.62
     noires
    0.60
    費
    0.59
     alone
    0.58
     coût
    0.58
     dikutip
    0.58
    Act Density 0.001%

    No Known Activations