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

    Neuronpedia

    INDEX
    Explanations

    weapons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Version
    -0.07
    -0.07
    (properties
    -0.07
     removeAll
    -0.07
     Diesel
    -0.07
    -0.06
    ...(
    -0.06
    .instructions
    -0.06
    -0.06
    TOKEN
    -0.06
    POSITIVE LOGITS
    ?):
    0.06
     кам
    0.06
     grands
    0.06
    496
    0.06
     Bam
    0.06
     podr
    0.06
     pudd
    0.06
    _crc
    0.06
    يط
    0.05
    єш
    0.05
    Act Density 0.479%

    No Known Activations