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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ┃
    -0.07
     türl
    -0.07
    pring
    -0.07
    .private
    -0.07
     avoid
    -0.07
     signify
    -0.07
    ibase
    -0.07
    ª
    -0.07
     Does
    -0.07
    .WARNING
    -0.06
    POSITIVE LOGITS
     subsets
    0.07
     sits
    0.07
     admittedly
    0.07
     centre
    0.07
    ﾛ
    0.07
    ኤ
    0.06
     balcony
    0.06
    ège
    0.06
    湿度
    0.06
     sitios
    0.06
    Act Density 0.063%

    No Known Activations