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

    Neuronpedia

    INDEX
    Explanations

    ip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fierce
    -0.08
    BS
    -0.07
    icl
    -0.06
    _selected
    -0.06
     fusion
    -0.06
    VEST
    -0.06
     control
    -0.06
    advance
    -0.06
     nors
    -0.06
    .None
    -0.06
    POSITIVE LOGITS
    不是
    0.07
     полез
    0.06
    .present
    0.06
     slippery
    0.06
     другие
    0.06
    =BitConverter
    0.06
     Katie
    0.06
     �
    0.06
    (DialogInterface
    0.06
    TECTED
    0.06
    Act Density 0.001%

    No Known Activations