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

    Neuronpedia

    INDEX
    Explanations

    Free offers and sign-ups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    도로
    -0.07
     Mari
    -0.07
     Kia
    -0.07
     Io
    -0.07
    Mari
    -0.06
     brunette
    -0.06
     Springs
    -0.06
     Rank
    -0.06
    ząd
    -0.06
    anned
    -0.06
    POSITIVE LOGITS
    049
    0.07
    radient
    0.07
    ton
    0.06
     potatoes
    0.06
    母
    0.06
    (course
    0.06
    !',
    0.06
     learner
    0.06
     partnership
    0.06
     residual
    0.06
    Act Density 0.000%

    No Known Activations