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

    Neuronpedia

    INDEX
    Explanations

    identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    645
    -0.07
     pent
    -0.07
    _primitive
    -0.07
    .scroll
    -0.07
     punct
    -0.07
     fingerprint
    -0.06
    65
    -0.06
     careful
    -0.06
    	long
    -0.06
     mushrooms
    -0.06
    POSITIVE LOGITS
    aler
    0.07
    -winning
    0.07
    änger
    0.06
    已经
    0.06
     úrov
    0.06
    _Timer
    0.06
     @"";↵
    0.06
     ITV
    0.06
    (),"
    0.06
     NBC
    0.06
    Act Density 0.025%

    No Known Activations