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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Messages
    -0.08
    BOOT
    -0.08
    _CODE
    -0.07
    (dd
    -0.07
    Visibility
    -0.07
    creasing
    -0.07
     unlocks
    -0.07
     nodded
    -0.07
    -camera
    -0.07
     Claus
    -0.07
    POSITIVE LOGITS
     SAFE
    0.06
    رز
    0.06
     etkili
    0.06
    errMsg
    0.06
     z
    0.06
    {\"
    0.05
    izando
    0.05
     materi
    0.05
    155
    0.05
     φω
    0.05
    Act Density 0.038%

    No Known Activations