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

    Neuronpedia

    INDEX
    Explanations

    kind/sort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    .respond
    -0.06
     Seems
    -0.06
     play
    -0.06
     admon
    -0.06
    _TRA
    -0.06
    ρά
    -0.06
     seaborn
    -0.06
    بال
    -0.06
    Then
    -0.06
    POSITIVE LOGITS
     uncertainty
    0.07
     multiline
    0.07
    .Kind
    0.07
    dives
    0.07
     certs
    0.07
    CurrentUser
    0.06
    enegro
    0.06
     millions
    0.06
    .createUser
    0.06
     yours
    0.06
    Act Density 0.028%

    No Known Activations