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

    Neuronpedia

    INDEX
    Explanations

    drying, curing, healing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اں
    0.61
     concierge
    0.57
     serviço
    0.57
     terrified
    0.54
    นี้
    0.54
     policing
    0.54
     televised
    0.51
     problème
    0.51
     sonar
    0.50
     זה
    0.49
    POSITIVE LOGITS
    ك
    0.75
    ح
    0.69
    к
    0.65
    м
    0.65
    ب
    0.63
    ла
    0.62
    ंग
    0.61
    و
    0.58
     megfelel
    0.57
     Counc
    0.54
    Act Density 0.005%

    No Known Activations