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
    c
    -0.12
    z
    -0.11
    e
    -0.11
    ch
    -0.10
    v
    -0.10
    a
    -0.10
    g
    -0.10
    m
    -0.10
    ()
↵
↵
    -0.10
    l
    -0.10
    POSITIVE LOGITS
    MAN
    0.06
    atri
    0.06
     �
    0.06
     PERSON
    0.06
    Serial
    0.06
    .readLine
    0.06
     PRE
    0.06
    _accept
    0.06
     Serial
    0.06
     nepř
    0.06
    Act Density 3.205%

    No Known Activations