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

    Neuronpedia

    INDEX
    Explanations

    power plants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hearty
    -0.07
     lengthy
    -0.07
    _tuple
    -0.06
    _j
    -0.06
     calculation
    -0.06
    頻
    -0.06
     spouse
    -0.06
    حم
    -0.06
    .nickname
    -0.06
    (ss
    -0.06
    POSITIVE LOGITS
    .Ultra
    0.06
    Leo
    0.06
    -red
    0.06
    InternalServerError
    0.06
    .↵↵↵
    0.06
    瓶
    0.06
    _targets
    0.06
     reversible
    0.06
     Đó
    0.06
    (ml
    0.06
    Act Density 0.022%

    No Known Activations