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

    Neuronpedia

    INDEX
    Explanations

    O

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '],
    -0.07
    /(
    -0.07
     denom
    -0.07
    matrix
    -0.06
     pink
    -0.06
    AIM
    -0.06
    ('~
    -0.06
     matlab
    -0.06
    ">(
    -0.06
    _STRING
    -0.06
    POSITIVE LOGITS
     yielded
    0.07
     třet
    0.06
     поє
    0.06
    　　　　　　　　　
    0.06
     pocit
    0.06
    VML
    0.06
    -products
    0.06
    仕
    0.06
    stal
    0.06
     gelecek
    0.06
    Act Density 0.008%

    No Known Activations