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

    Neuronpedia

    INDEX
    Explanations

    duties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Construction
    -0.07
    态
    -0.06
     recreational
    -0.06
     quicker
    -0.06
     addUser
    -0.06
     Phi
    -0.06
     xamarin
    -0.06
     PHYS
    -0.06
     Üniversit
    -0.06
    .upper
    -0.06
    POSITIVE LOGITS
    توان
    0.06
     PD
    0.06
    lags
    0.06
     sculpt
    0.06
     euler
    0.06
    970
    0.06
    ван
    0.06
    witter
    0.06
    رود
    0.06
    gens
    0.06
    Act Density 0.123%

    No Known Activations