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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LineStyle
    -0.07
     разд
    -0.06
    _render
    -0.06
     consulate
    -0.06
    งส
    -0.06
     generously
    -0.06
     �
    -0.06
     devout
    -0.06
    heartbeat
    -0.06
     Undert
    -0.06
    POSITIVE LOGITS
     davranış
    0.06
     -----↵
    0.06
     HinderedRotor
    0.06
    »
    0.06
    」↵
    0.06
    ื
    0.06
     removed
    0.06
     their
    0.06
    Stub
    0.06
     Blick
    0.06
    Act Density 0.003%

    No Known Activations