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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    岡
    -0.07
    INET
    -0.07
    -parameter
    -0.07
    _Service
    -0.07
    Canonical
    -0.07
    LETED
    -0.07
    А
    -0.07
     occup
    -0.06
    ValidationError
    -0.06
     Zust
    -0.06
    POSITIVE LOGITS
     '{{
    0.06
    [mid
    0.06
     SAX
    0.06
     spaceship
    0.06
     Leo
    0.06
     即
    0.05
    gnu
    0.05
     ruler
    0.05
    ?>"></
    0.05
     gấp
    0.05
    Act Density 0.008%

    No Known Activations