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

    Neuronpedia

    INDEX
    Explanations

    skip special tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Metadata
    0.44
    Adam
    0.41
    Spectral
    0.38
    Metro
    0.38
    يمي
    0.37
    Longitude
    0.37
    Memory
    0.36
    META
    0.36
    Envelope
    0.36
     amn
    0.36
    POSITIVE LOGITS
    볶
    0.36
     kg
    0.36
     Classes
    0.35
     taux
    0.34
     étages
    0.34
     lấy
    0.34
     भाज
    0.34
     어떤
    0.33
    lambda
    0.33
     자기
    0.33
    Act Density 0.003%

    No Known Activations