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

    Neuronpedia

    INDEX
    Explanations

    -related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thaimassage
    -0.07
    рование
    -0.07
     Third
    -0.06
    ClassName
    -0.06
    NamedQuery
    -0.06
     Mal
    -0.06
    ####
    -0.06
    Mal
    -0.06
    Opening
    -0.06
     functools
    -0.06
    POSITIVE LOGITS
    -red
    0.07
     seja
    0.07
    HT
    0.07
    013
    0.06
    oute
    0.06
    mant
    0.06
    證
    0.06
     calculations
    0.06
     incentiv
    0.06
     yelled
    0.06
    Act Density 0.003%

    No Known Activations