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

    Neuronpedia

    INDEX
    Explanations

    counting or ranking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $
    0.45
    ിയ
    0.44
     새로운
    0.44
     &
    0.42
    ch
    0.42
     التح
    0.42
    new
    0.41
    Data
    0.40
    rat
    0.40
    D
    0.40
    POSITIVE LOGITS
     harming
    0.53
     músculos
    0.49
     inflicted
    0.49
    ochlor
    0.49
     defra
    0.48
     instituted
    0.47
     угла
    0.45
    liğini
    0.45
     guides
    0.44
    iarism
    0.44
    Act Density 0.000%

    No Known Activations