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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fought
    -0.07
     Scrap
    -0.06
     characteristic
    -0.06
    redit
    -0.06
     přičemž
    -0.06
    /pm
    -0.06
     retval
    -0.06
    ungeon
    -0.06
     ル
    -0.06
     cross
    -0.06
    POSITIVE LOGITS
    忠
    0.07
    _plugin
    0.07
     подк
    0.07
    (sin
    0.07
    kil
    0.06
    ifle
    0.06
    _tA
    0.06
    _ag
    0.06
    、何
    0.06
     स
    0.06
    Act Density 0.000%

    No Known Activations