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

    Neuronpedia

    INDEX
    Explanations

    potential drawbacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ယ
    0.50
     pretended
    0.45
     rightfully
    0.45
     phospholipids
    0.43
     depended
    0.41
     masti
    0.40
     ferromagnetic
    0.40
    üsseldorf
    0.39
     facilitators
    0.39
     swabs
    0.39
    POSITIVE LOGITS
    1
    0.65
    sample
    0.49
    Ή
    0.48
    plus
    0.47
    resident
    0.47
    כנס
    0.46
    reactor
    0.46
     Reaper
    0.46
    samp
    0.45
    хоро
    0.45
    Act Density 0.000%

    No Known Activations