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

    Neuronpedia

    INDEX
    Explanations

    say "I" or "One"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    can
    -0.07
     admirable
    -0.07
    <tr
    -0.06
    らく
    -0.06
    cer
    -0.06
     describe
    -0.06
    าษ
    -0.06
     ["
    -0.06
     Roch
    -0.06
     fulfill
    -0.06
    POSITIVE LOGITS
     Homework
    0.07
    recipient
    0.06
    センター
    0.06
     indis
    0.06
    LOCATION
    0.06
     UIAlert
    0.06
    ΟΥΣ
    0.06
    ��
    0.06
    .RED
    0.06
    цен
    0.06
    Act Density 0.034%

    No Known Activations