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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    larını
    -0.07
     판
    -0.07
    _subs
    -0.06
    Ars
    -0.06
    _pl
    -0.06
    	controller
    -0.06
    任何
    -0.06
     homosex
    -0.06
    Když
    -0.06
    icide
    -0.06
    POSITIVE LOGITS
    (animated
    0.06
    GEST
    0.06
     Lemma
    0.06
    ]↵↵
    0.06
    .styleable
    0.06
    .apple
    0.06
    iếng
    0.06
    _Run
    0.06
    [char
    0.06
    .asp
    0.06
    Act Density 0.026%

    No Known Activations