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

    Neuronpedia

    INDEX
    Explanations

    Saying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    semblies
    -0.08
     Cu
    -0.07
    copies
    -0.07
     Lies
    -0.07
    \Controller
    -0.07
     teknik
    -0.07
     shred
    -0.06
    $total
    -0.06
    equipment
    -0.06
    サイト
    -0.06
    POSITIVE LOGITS
    ename
    0.06
    ..........
    0.06
     autom
    0.06
     použit
    0.06
    .....
    0.06
     напит
    0.06
    例如
    0.05
     flair
    0.05
     unreliable
    0.05
    -me
    0.05
    Act Density 0.018%

    No Known Activations