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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -valu
    -0.07
     Auch
    -0.07
     masturbating
    -0.07
     ques
    -0.06
     Sharia
    -0.06
     height
    -0.06
    path
    -0.06
     sausage
    -0.06
     chemotherapy
    -0.06
     بنابر
    -0.06
    POSITIVE LOGITS
    	error
    0.07
    236
    0.07
    uder
    0.06
     quantum
    0.06
    _SPEC
    0.06
     CLUB
    0.06
    VIS
    0.06
     Humanity
    0.06
     dwelling
    0.06
    ovsky
    0.06
    Act Density 0.112%

    No Known Activations