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

    Neuronpedia

    INDEX
    Explanations

    events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inecraft
    -0.07
     fh
    -0.07
     principally
    -0.07
     Usually
    -0.06
    -mouth
    -0.06
     España
    -0.06
     руки
    -0.06
     descend
    -0.06
    银行
    -0.06
    のような
    -0.06
    POSITIVE LOGITS
     UserProfile
    0.08
    ?!↵↵
    0.06
    .Options
    0.06
    _decorator
    0.06
    /User
    0.06
    _TRANSL
    0.06
    ()?
    0.06
     forKey
    0.06
     $('[
    0.06
    ска
    0.06
    Act Density 0.224%

    No Known Activations