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

    Neuronpedia

    INDEX
    Explanations

    str

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alec
    -0.08
    Calculate
    -0.08
    <=
    -0.07
    ដ
    -0.07
    (curl
    -0.07
    撇
    -0.07
     Drone
    -0.07
    뎌
    -0.07
     Burlington
    -0.07
    Michelle
    -0.07
    POSITIVE LOGITS
     Routine
    0.07
    Fortunately
    0.07
    فيد
    0.07
     situ
    0.07
     animations
    0.07
     nation
    0.07
    guna
    0.07
     tense
    0.07
    &quot
    0.06
    requests
    0.06
    Act Density 0.003%

    No Known Activations