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

    Neuronpedia

    INDEX
    Explanations

    file configurations and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ob
    -0.07
     surrounded
    -0.06
     Chop
    -0.06
     podrob
    -0.06
    很
    -0.06
     Со
    -0.06
     řek
    -0.06
     mũi
    -0.06
    struk
    -0.06
     dara
    -0.06
    POSITIVE LOGITS
     offices
    0.07
    _NAME
    0.07
     Token
    0.07
    uple
    0.07
     confusing
    0.07
     discount
    0.07
    ерина
    0.06
    -transition
    0.06
    -cat
    0.06
    _discount
    0.06
    Act Density 0.000%

    No Known Activations