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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Attachments
    -0.07
    inars
    -0.07
    PasswordField
    -0.07
     Printed
    -0.07
     lions
    -0.07
     contacts
    -0.07
     Lena
    -0.06
    qua
    -0.06
     cho
    -0.06
     comparing
    -0.06
    POSITIVE LOGITS
     belirli
    0.06
     genders
    0.06
    ain
    0.06
    _MINOR
    0.06
    .ga
    0.06
    _ISS
    0.06
    idan
    0.05
    setState
    0.05
    .sleep
    0.05
    ?>;↵
    0.05
    Act Density 0.003%

    No Known Activations