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

    Neuronpedia

    INDEX
    Explanations

    EEP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç
    -0.08
    owane
    -0.07
    utan
    -0.06
     brilliant
    -0.06
    408
    -0.06
    ots
    -0.06
    िसम
    -0.06
     مقد
    -0.06
    appropri
    -0.06
    ged
    -0.06
    POSITIVE LOGITS
    BP
    0.09
    P
    0.08
    OP
    0.08
     lp
    0.07
    drop
    0.07
     Crunch
    0.07
     Manufacturer
    0.07
    umbotron
    0.07
    habit
    0.06
     taxpayer
    0.06
    Act Density 0.086%

    No Known Activations