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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Visual
    0.39
    Gram
    0.39
    LayoutParams
    0.39
    MaxWidth
    0.38
    Conceptual
    0.38
     visuals
    0.38
    LOOK
    0.37
    നോ
    0.37
     طرح
    0.36
    Authent
    0.36
    POSITIVE LOGITS
     sensed
    0.42
    änglich
    0.41
     sớm
    0.41
     kesel
    0.40
    zco
    0.39
     delighted
    0.39
     chur
    0.39
     lediglich
    0.39
     lesser
    0.38
     belted
    0.38
    Act Density 0.000%

    No Known Activations