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

    Neuronpedia

    INDEX
    Explanations

    say "list"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .My
    -0.07
    ume
    -0.07
    essay
    -0.07
     beck
    -0.06
     iff
    -0.06
    Miss
    -0.06
     tunnel
    -0.06
    sts
    -0.06
    ᭺
    -0.06
    .TryGetValue
    -0.06
    POSITIVE LOGITS
    (store
    0.07
     smith
    0.07
    سير
    0.07
     grotes
    0.06
    DEPTH
    0.06
    注销
    0.06
     fileprivate
    0.06
    _scheme
    0.06
    Collector
    0.06
    _stream
    0.06
    Act Density 0.004%

    No Known Activations