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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hammer
    -0.07
     разд
    -0.06
     imper
    -0.06
     Imper
    -0.06
     вваж
    -0.06
    ira
    -0.06
    ृत
    -0.06
     pastor
    -0.06
     май
    -0.06
     Shake
    -0.06
    POSITIVE LOGITS
    @extends
    0.07
     pinterest
    0.07
     Reds
    0.07
     chords
    0.06
     pokemon
    0.06
    insurance
    0.06
    .object
    0.06
     Wine
    0.06
     fries
    0.06
    >If
    0.06
    Act Density 0.000%

    No Known Activations