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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    あの
    -0.07
    _cust
    -0.06
     Wo
    -0.06
    ainty
    -0.06
    _decay
    -0.06
    INST
    -0.06
     Syrians
    -0.06
     상대
    -0.06
    kud
    -0.06
    	ext
    -0.06
    POSITIVE LOGITS
    .TRAILING
    0.06
    configs
    0.06
    'є
    0.06
    .ToolStripButton
    0.06
    criminal
    0.06
     stab
    0.06
     ).↵↵
    0.06
    _TRNS
    0.06
     Nothing
    0.06
    iliate
    0.06
    Act Density 0.010%

    No Known Activations