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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ý
    -0.07
    backs
    -0.07
    _ur
    -0.06
    orias
    -0.06
    _EDITOR
    -0.06
     lyr
    -0.06
     reduction
    -0.06
    ��
    -0.06
    aut
    -0.06
    ällt
    -0.06
    POSITIVE LOGITS
    cast
    0.06
    listening
    0.06
     Chapman
    0.06
     nhánh
    0.06
    arro
    0.06
    491
    0.06
     '<%=
    0.05
    REST
    0.05
     mad
    0.05
     Người
    0.05
    Act Density 0.022%

    No Known Activations