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

    Neuronpedia

    INDEX
    Explanations

    examining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PROGRAM
    -0.07
    vsp
    -0.07
    　l
    -0.07
    　ｌ
    -0.06
    浜
    -0.06
     jac
    -0.06
     Playoff
    -0.06
    قع
    -0.06
     nebezpeč
    -0.06
    infos
    -0.06
    POSITIVE LOGITS
    oad
    0.08
    _ELEM
    0.07
    array
    0.07
    (LL
    0.07
    ocrats
    0.07
     discouraged
    0.06
     �
    0.06
    ollision
    0.06
    _android
    0.06
    	current
    0.06
    Act Density 0.039%

    No Known Activations