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

    Neuronpedia

    INDEX
    Explanations

    enough

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CHA
    -0.08
    ชนะ
    -0.07
     $_
    -0.07
    ובר
    -0.07
    RA
    -0.07
     drill
    -0.07
    (match
    -0.07
    $(".
    -0.07
    强迫
    -0.07
    ף
    -0.07
    POSITIVE LOGITS
    �
    0.07
     rusty
    0.07
     cru
    0.07
    삳
    0.07
     Lamp
    0.06
    (tol
    0.06
    ログ
    0.06
     Mem
    0.06
    这般
    0.06
     botanical
    0.06
    Act Density 0.147%

    No Known Activations