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

    Neuronpedia

    INDEX
    Explanations

    closing HTML tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    ке
    -0.06
    underline
    -0.06
     antioxidants
    -0.06
     inet
    -0.06
    yang
    -0.06
     malfunction
    -0.06
     regret
    -0.06
     rationale
    -0.06
     kể
    -0.06
    POSITIVE LOGITS
     उच
    0.07
    "?↵↵
    0.06
    ilities
    0.06
     ді
    0.06
    icum
    0.06
    Bow
    0.06
    ppo
    0.06
    -х
    0.06
    ：<
    0.06
    /bg
    0.06
    Act Density 0.007%

    No Known Activations