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

    Neuronpedia

    INDEX
    Explanations

    make

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harassing
    -0.07
     prompting
    -0.07
     výzkum
    -0.06
     Params
    -0.06
    Element
    -0.06
     pornô
    -0.06
    (InitializedTypeInfo
    -0.06
    уйте
    -0.06
     construct
    -0.06
     Period
    -0.06
    POSITIVE LOGITS
     Ελλά
    0.07
    (mac
    0.07
     testified
    0.06
     incid
    0.06
     Rag
    0.06
    zí
    0.06
     scar
    0.06
    sx
    0.06
     musica
    0.06
    _BACKGROUND
    0.06
    Act Density 0.001%

    No Known Activations