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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    keleton
    0.40
     Electron
    0.37
     XOR
    0.37
    orpions
    0.37
     berger
    0.36
    ifer
    0.36
    htar
    0.36
     Coat
    0.35
    quet
    0.34
    स्पति
    0.34
    POSITIVE LOGITS
    而已
    0.44
    calc
    0.39
    running
    0.38
     እየ
    0.38
    だけ
    0.38
    favor
    0.36
     calc
    0.36
     alleine
    0.36
     ਉਨ੍ਹਾਂ
    0.36
     അനുഭവ
    0.36
    Act Density 0.002%

    No Known Activations