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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infographic
    -0.07
    .Win
    -0.07
    -↵↵
    -0.06
    _MET
    -0.06
    _COLLECTION
    -0.06
    .Me
    -0.06
    >tag
    -0.06
    _loan
    -0.06
    (clock
    -0.06
     الله
    -0.06
    POSITIVE LOGITS
     tháng
    0.07
    rical
    0.07
    	state
    0.06
    enler
    0.06
     topical
    0.06
     начала
    0.06
    ard
    0.06
     positional
    0.06
     faults
    0.06
    权
    0.06
    Act Density 0.000%

    No Known Activations