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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enviar
    -0.07
    -static
    -0.07
    ư
    -0.07
    画面
    -0.07
    Link
    -0.07
    ası
    -0.07
    创始
    -0.07
    addAll
    -0.06
    ölü
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    LOCATION
    0.07
    绑架
    0.07
     Rick
    0.07
    unde
    0.07
    _TRANS
    0.07
     restrained
    0.07
     cater
    0.07
    ████
    0.07
     BAT
    0.07
    强行
    0.07
    Act Density 0.082%

    No Known Activations