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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .one
    -0.06
     accumulation
    -0.06
    ’’
    -0.06
     exhibited
    -0.06
    _UNIFORM
    -0.06
     stupid
    -0.06
     palindrome
    -0.06
    mh
    -0.06
     konusunda
    -0.06
    agar
    -0.06
    POSITIVE LOGITS
     Coast
    0.07
    afen
    0.07
     conced
    0.06
    ileges
    0.06
     Overse
    0.06
     ارد
    0.06
     currentDate
    0.06
    áln
    0.06
     senate
    0.06
     ParseException
    0.06
    Act Density 0.033%

    No Known Activations