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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ooky
    -0.07
     забезпечення
    -0.07
    .hu
    -0.06
    iga
    -0.06
     Ug
    -0.06
    ��
    -0.06
     Chin
    -0.06
     accur
    -0.06
    測
    -0.06
     […]↵↵
    -0.06
    POSITIVE LOGITS
     acceptable
    0.07
     SUBJECT
    0.07
     panc
    0.07
     command
    0.07
     accountable
    0.07
    command
    0.06
    名称
    0.06
     Olympic
    0.06
    missible
    0.06
    इसक
    0.06
    Act Density 0.020%

    No Known Activations