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

    Neuronpedia

    INDEX
    Explanations

    short range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    _bt
    -0.07
    ekt
    -0.06
    wargs
    -0.06
     inve
    -0.06
     Kits
    -0.06
     ventana
    -0.06
    formula
    -0.05
     وزار
    -0.05
    牙
    -0.05
    POSITIVE LOGITS
     sneak
    0.07
    suspend
    0.07
    _modified
    0.07
    bringing
    0.07
    woke
    0.07
    APT
    0.07
    UTF
    0.06
     invoke
    0.06
     prime
    0.06
    _paint
    0.06
    Act Density 0.038%

    No Known Activations