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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ِ
    -0.07
     있다고
    -0.07
    센
    -0.07
     METHOD
    -0.06
     aside
    -0.06
    enable
    -0.06
     sen
    -0.06
     있다는
    -0.06
     корп
    -0.06
     GetString
    -0.06
    POSITIVE LOGITS
     розвитку
    0.07
    baar
    0.06
     Submit
    0.06
    .Persistent
    0.06
    __',
    0.06
    ulls
    0.06
    (graph
    0.06
     عامة
    0.06
    fgang
    0.06
     mutated
    0.06
    Act Density 0.011%

    No Known Activations