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

    Neuronpedia

    INDEX
    Explanations

    Abstract concepts/societal issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    voices
    -0.07
    inst
    -0.06
    91
    -0.06
    ़ो
    -0.06
    meeting
    -0.06
     dt
    -0.06
     slide
    -0.06
     championships
    -0.06
     перес
    -0.06
    主
    -0.06
    POSITIVE LOGITS
     kvin
    0.06
     �
    0.06
     Анд
    0.06
    _HS
    0.06
     sudah
    0.06
    /task
    0.06
     LANG
    0.06
    ある
    0.06
    verige
    0.06
     Afrika
    0.06
    Act Density 0.132%

    No Known Activations