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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inherits
    -0.06
    ze
    -0.06
     Diaz
    -0.06
    間に
    -0.06
    zones
    -0.06
     […]
    -0.06
     Meyer
    -0.06
    ix
    -0.06
     jednodu
    -0.06
     Αυ
    -0.06
    POSITIVE LOGITS
     Parenthood
    0.08
    ddit
    0.07
     specialist
    0.07
     peter
    0.06
    ........................
    0.06
    .getMinutes
    0.06
     首页
    0.06
     interested
    0.06
    Forget
    0.06
     uncomfortable
    0.06
    Act Density 0.000%

    No Known Activations