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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     INCLUDE
    -0.08
     temporada
    -0.08
     microphone
    -0.07
     LEVEL
    -0.07
    “Our
    -0.07
    "Our
    -0.07
     Concent
    -0.07
     traveller
    -0.07
    _depend
    -0.07
    gressive
    -0.06
    POSITIVE LOGITS
     correlate
    0.06
    ำ
    0.06
    []>
    0.06
    .Dictionary
    0.06
     chlor
    0.06
    pcf
    0.06
     unfit
    0.06
    ,Object
    0.06
    δει
    0.06
    .fe
    0.06
    Act Density 0.014%

    No Known Activations