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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brewing
    -0.07
     archive
    -0.07
     Dil
    -0.06
    ництво
    -0.06
     Triangle
    -0.06
     Transition
    -0.06
     हट
    -0.06
     itibar
    -0.06
     土
    -0.06
     نو
    -0.06
    POSITIVE LOGITS
     mim
    0.07
    ��
    0.07
    ivo
    0.07
    Reducer
    0.06
    _sensitive
    0.06
     yo
    0.06
     ràng
    0.06
    norm
    0.06
    __
↵
    0.06
    强
    0.06
    Act Density 0.089%

    No Known Activations