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

    Neuronpedia

    INDEX
    Explanations

    features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     채용
    -0.07
     lado
    -0.06
    .transitions
    -0.06
     larvae
    -0.06
    Pot
    -0.06
     cosmic
    -0.06
     datos
    -0.06
    _cover
    -0.06
     Latin
    -0.06
    ично
    -0.06
    POSITIVE LOGITS
     foremost
    0.07
    นะ
    0.06
     rugged
    0.06
    ชนะ
    0.06
    .learning
    0.06
    (pool
    0.06
    든
    0.06
    (ticket
    0.06
     fifteen
    0.06
    generate
    0.06
    Act Density 0.016%

    No Known Activations