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

    Neuronpedia

    INDEX
    Explanations

    /-

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    톤
    -0.07
    'http
    -0.06
    Concern
    -0.06
    diamond
    -0.06
    切
    -0.06
    ensure
    -0.06
    Stats
    -0.06
    租
    -0.06
    ैठ
    -0.06
    west
    -0.06
    POSITIVE LOGITS
    -pos
    0.07
     жод
    0.07
    /fl
    0.06
     Exceptions
    0.06
    (ft
    0.06
    ('__
    0.06
     hav
    0.06
     $#
    0.06
    ivo
    0.06
     možné
    0.06
    Act Density 0.001%

    No Known Activations