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

    Neuronpedia

    INDEX
    Explanations

    charge or discharge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    11
    -0.08
     kuvvet
    -0.06
    439
    -0.06
    ören
    -0.06
     zus
    -0.06
    aphael
    -0.06
    Best
    -0.06
    909
    -0.06
     Evil
    -0.06
     Raq
    -0.06
    POSITIVE LOGITS
     discharged
    0.10
     discharge
    0.09
     mischief
    0.07
    charges
    0.07
     Dust
    0.07
    ica
    0.07
     �
    0.07
     acoustic
    0.07
    Water
    0.07
     Water
    0.07
    Act Density 0.005%

    No Known Activations