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

    Neuronpedia

    INDEX
    Explanations

    Problems and solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Borg
    -0.07
    terror
    -0.07
     çalışmaları
    -0.07
    quivo
    -0.06
     CrossAxisAlignment
    -0.06
    оглас
    -0.06
     руку
    -0.06
    उ
    -0.06
    .radius
    -0.06
     Incre
    -0.06
    POSITIVE LOGITS
     GA
    0.07
     unreasonable
    0.06
    Creating
    0.06
    ({↵↵
    0.06
    }_
    0.06
     Namespace
    0.06
    lations
    0.06
    _on
    0.06
     Let
    0.06
     ])↵↵
    0.06
    Act Density 0.272%

    No Known Activations