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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stit
    -0.06
    elif
    -0.06
     minds
    -0.06
    capitalize
    -0.06
    ..:
    -0.06
     mind
    -0.06
     разработ
    -0.06
    [name
    -0.06
    umuz
    -0.06
    azed
    -0.06
    POSITIVE LOGITS
     backwards
    0.07
     backward
    0.06
     台
    0.06
    Supported
    0.06
    298
    0.06
     동일
    0.06
     後
    0.06
    ��
    0.06
     položky
    0.06
     took
    0.06
    Act Density 0.014%

    No Known Activations