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

    Neuronpedia

    INDEX
    Explanations

    imperative verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    苧
    -0.07
    leurs
    -0.07
    Z
    -0.07
    zą
    -0.07
    lds
    -0.07
    sequently
    -0.07
     cathedral
    -0.06
    穴位
    -0.06
    cluded
    -0.06
     Cooler
    -0.06
    POSITIVE LOGITS
    (object
    0.08
    アイテ
    0.07
    ﭟ
    0.07
    ipc
    0.07
    ائل
    0.06
     artifacts
    0.06
    )initWithFrame
    0.06
    탉
    0.06
    _PARENT
    0.06
    Shows
    0.06
    Act Density 0.029%

    No Known Activations