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

    Neuronpedia

    INDEX
    Explanations

    HB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    averse
    -0.08
    🚐
    -0.07
    izens
    -0.07
     Licensed
    -0.07
     listeners
    -0.07
    죌
    -0.07
     geliştir
    -0.07
    ocker
    -0.07
     Olsen
    -0.07
    組織
    -0.07
    POSITIVE LOGITS
    支配
    0.07
    泄漏
    0.07
    氰
    0.07
     permanently
    0.07
    大发
    0.07
    ям
    0.07
     abbiamo
    0.07
    قر
    0.07
     całego
    0.06
     (&
    0.06
    Act Density 0.008%

    No Known Activations