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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ates
    -0.07
    Hand
    -0.06
    ISED
    -0.06
    .getName
    -0.06
    ноз
    -0.06
    าน
    -0.06
    ATES
    -0.06
    ard
    -0.06
    lore
    -0.06
    red
    -0.06
    POSITIVE LOGITS
    .Warning
    0.07
    _Callback
    0.07
    (success
    0.07
    .Named
    0.06
     Stored
    0.06
    退
    0.06
    _;↵↵
    0.06
    _ARM
    0.06
     Min
    0.06
     },↵↵
    0.06
    Act Density 0.016%

    No Known Activations