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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Working
    -0.06
    _sta
    -0.06
    etes
    -0.06
    	ll
    -0.06
    ंड
    -0.06
    ドラ
    -0.06
     sos
    -0.06
    iali
    -0.06
    народ
    -0.06
    sales
    -0.06
    POSITIVE LOGITS
    uche
    0.06
    /token
    0.06
     mirror
    0.06
    bulk
    0.06
     verbally
    0.06
     SE
    0.06
     consul
    0.06
    msgs
    0.06
    _interval
    0.06
    -shadow
    0.06
    Act Density 0.218%

    No Known Activations