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

    Neuronpedia

    INDEX
    Explanations

    scheduling meetings workouts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exploration
    -0.09
    ्सा
    -0.08
    .correct
    -0.08
    %s
    -0.07
     আশ
    -0.07
     overarching
    -0.07
    øs
    -0.07
     Exploration
    -0.07
    �
    -0.07
    土
    -0.07
    POSITIVE LOGITS
    Argb
    0.09
    reshold
    0.08
     ભરતી
    0.08
    itched
    0.08
     அன்று
    0.08
     જોડ
    0.08
     તાલ
    0.08
     degelijk
    0.08
     kwaliteit
    0.07
     કાર્યવ
    0.07
    Act Density 0.002%

    No Known Activations