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

    Neuronpedia

    INDEX
    Explanations

    altitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terrorist
    -0.07
    aporation
    -0.06
    圍
    -0.06
     voice
    -0.06
     Hannity
    -0.06
    aries
    -0.06
    InvalidArgumentException
    -0.06
    copies
    -0.06
    tablename
    -0.06
     correlates
    -0.06
    POSITIVE LOGITS
    caster
    0.07
    arti
    0.07
    			↵↵
    0.06
    chner
    0.06
    [].
    0.06
     fled
    0.06
    weetalert
    0.06
    !↵↵↵↵
    0.06
     Github
    0.06
      ↵↵↵
    0.06
    Act Density 0.009%

    No Known Activations