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

    Neuronpedia

    INDEX
    Explanations

    oc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     climbed
    -0.07
     influx
    -0.07
     salvage
    -0.07
    ucked
    -0.07
    群
    -0.06
     dolaş
    -0.06
    ２
    -0.06
     migrate
    -0.06
     runnable
    -0.06
    lags
    -0.06
    POSITIVE LOGITS
    PROP
    0.07
    forman
    0.07
    _DM
    0.06
     MMO
    0.06
    _kernel
    0.06
     آس
    0.06
    Ma
    0.06
    -aware
    0.06
    ?>
↵
    0.06
    /back
    0.06
    Act Density 0.002%

    No Known Activations