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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dě
    -0.07
    ниця
    -0.06
    éry
    -0.06
    щини
    -0.06
    (obs
    -0.06
    らく
    -0.06
    hawk
    -0.06
    どう
    -0.06
    背
    -0.06
    .matcher
    -0.06
    POSITIVE LOGITS
     Cindy
    0.07
     permitting
    0.07
     popover
    0.06
     iktidar
    0.06
     DialogInterface
    0.06
    .compareTo
    0.06
     Include
    0.06
     Luo
    0.06
     Nová
    0.06
     mildly
    0.06
    Act Density 0.000%

    No Known Activations