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

    Neuronpedia

    INDEX
    Explanations

    Programming tests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -----
    -0.07
     Krank
    -0.07
     Foods
    -0.06
     Charts
    -0.06
     chant
    -0.06
    Swap
    -0.06
     _____
    -0.06
    ฤษภาคม
    -0.06
     Fi
    -0.06
    :::
    -0.06
    POSITIVE LOGITS
     Optim
    0.08
    still
    0.08
    .cod
    0.07
    έ
    0.07
     Griff
    0.06
     بال
    0.06
    -quality
    0.06
     ضربه
    0.06
    ुकस
    0.06
    �
    0.06
    Act Density 0.025%

    No Known Activations