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

    Neuronpedia

    INDEX
    Explanations

    copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Semantic
    -0.08
     指
    -0.07
    Walking
    -0.06
    */,
    -0.06
    (keyword
    -0.06
    %n
    -0.06
    $path
    -0.06
    (team
    -0.06
    Ak
    -0.06
     ☆
    -0.06
    POSITIVE LOGITS
     vital
    0.06
    個
    0.06
    hlen
    0.06
    ingly
    0.06
    ecret
    0.06
    Dst
    0.06
     fend
    0.06
    oved
    0.06
    θν
    0.06
    ungi
    0.06
    Act Density 0.001%

    No Known Activations