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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诱发
    -0.07
    /www
    -0.07
     $("#
    -0.07
    ential
    -0.07
    _push
    -0.06
     stochastic
    -0.06
    INATION
    -0.06
    野外
    -0.06
     О
    -0.06
    馁
    -0.06
    POSITIVE LOGITS
    亲友
    0.07
    Entry
    0.07
    kreśl
    0.07
    Prog
    0.07
    texts
    0.07
    �
    0.07
    'It
    0.07
     detector
    0.06
    挫
    0.06
    �
    0.06
    Act Density 0.008%

    No Known Activations