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

    Neuronpedia

    INDEX
    Explanations

    uhe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     발견
    -0.07
    [mask
    -0.07
     hdc
    -0.07
     reverence
    -0.06
    IU
    -0.06
     BLE
    -0.06
    ไซ
    -0.06
     bord
    -0.06
    _TRANSL
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    pres
    0.06
    ありがとう
    0.06
     archive
    0.06
    acular
    0.06
     pairs
    0.06
     arose
    0.06
     Surge
    0.06
     practicing
    0.06
     episode
    0.06
    리는
    0.06
    Act Density 0.322%

    No Known Activations