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

    Neuronpedia

    INDEX
    Explanations

    Judging true or false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guint
    -0.09
     gush
    -0.08
     thrilled
    -0.07
    SELECT
    -0.07
     ensuring
    -0.07
     vyb
    -0.07
     еж
    -0.07
    c
    -0.07
     throughput
    -0.07
     सूत्र
    -0.07
    POSITIVE LOGITS
    .FALSE
    0.11
    (success
    0.10
     fals
    0.10
     FALSE
    0.09
     misinformation
    0.09
    (false
    0.09
     False
    0.09
    真假
    0.09
    .false
    0.09
     여부
    0.09
    Act Density 0.018%

    No Known Activations