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

    Neuronpedia

    INDEX
    Explanations

    considered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     množ
    -0.07
     πάνω
    -0.07
    -wow
    -0.07
    _nav
    -0.07
     dopad
    -0.07
     facto
    -0.07
     cả
    -0.07
    _elems
    -0.07
    _os
    -0.06
    DataReader
    -0.06
    POSITIVE LOGITS
     đốc
    0.06
    	trace
    0.06
    geom
    0.06
     approved
    0.06
    شن
    0.06
     Highlands
    0.05
     Outline
    0.05
    AppName
    0.05
     biểu
    0.05
    punk
    0.05
    Act Density 0.058%

    No Known Activations