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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Psi
    -0.06
     flowed
    -0.06
     eaten
    -0.06
     intellectual
    -0.06
    859
    -0.06
     manpower
    -0.06
     Institutes
    -0.06
    841
    -0.06
    ीण
    -0.06
     cuales
    -0.06
    POSITIVE LOGITS
    \param
    0.07
     trag
    0.07
     bitwise
    0.07
     návr
    0.07
     fundraising
    0.06
     OST
    0.06
     nargin
    0.06
     THANK
    0.06
     AAP
    0.06
     マ
    0.06
    Act Density 0.029%

    No Known Activations