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

    Neuronpedia

    INDEX
    Explanations

    Benef

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    a
    -0.10
    e
    -0.10
    z
    -0.10
    c
    -0.10
    k
    -0.10
    ch
    -0.10
    v
    -0.10
    ()
↵
↵
    -0.09
    b
    -0.09
    l
    -0.09
    POSITIVE LOGITS
     PRE
    0.07
     Syn
    0.07
    Serial
    0.06
    ,&
    0.06
    PARATOR
    0.06
    longleftrightarrow
    0.06
     Dale
    0.06
    Driving
    0.06
    ุปกรณ
    0.06
    Projected
    0.06
    Act Density 2.100%

    No Known Activations