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
     Huang
    -0.06
     Pressure
    -0.06
     login
    -0.06
     plum
    -0.06
     Labs
    -0.06
     setTitle
    -0.06
    .,
    -0.06
     desert
    -0.06
    毫
    -0.06
    POSITIVE LOGITS
    造
    0.07
    wish
    0.07
    _GRP
    0.06
     рез
    0.06
    isan
    0.06
    амп
    0.06
    avana
    0.06
    .features
    0.06
    fw
    0.06
     unconscious
    0.06
    Act Density 0.058%

    No Known Activations