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

    Neuronpedia

    INDEX
    Explanations

    male names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bear
    -0.08
    γκ
    -0.08
    hi
    -0.07
     ).
    -0.06
     clinic
    -0.06
    gte
    -0.06
    RAD
    -0.06
     researcher
    -0.06
    ebin
    -0.06
    917
    -0.06
    POSITIVE LOGITS
     buena
    0.06
     cmds
    0.06
     Everyday
    0.06
     lk
    0.06
     الصف
    0.06
    >Login
    0.06
    وليو
    0.06
    -/
    0.06
    ,password
    0.06
    $body
    0.06
    Act Density 0.040%

    No Known Activations