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

    Neuronpedia

    INDEX
    Explanations

    Crime reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initiator
    -0.06
     relativ
    -0.06
    Selection
    -0.06
    Extract
    -0.06
     initiating
    -0.06
    _flg
    -0.06
    	Grid
    -0.05
     Implements
    -0.05
     Assistance
    -0.05
    _METADATA
    -0.05
    POSITIVE LOGITS
    hart
    0.07
    689
    0.07
    ponder
    0.07
    нем
    0.07
    вай
    0.07
    (mark
    0.07
    кий
    0.06
     —
    0.06
     $"{
    0.06
     plummet
    0.06
    Act Density 0.023%

    No Known Activations