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

    Neuronpedia

    INDEX
    Explanations

    mumbled or stammered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Recreational
    0.71
    まるで
    0.66
     Consultation
    0.65
    Powerful
    0.65
    Discovery
    0.63
    Tyr
    0.61
     consultations
    0.61
    Murder
    0.60
     Discovery
    0.59
    Evaluation
    0.58
    POSITIVE LOGITS
    ேயே
    0.85
    ꯟ
    0.84
     फायदा
    0.83
    ⊔
    0.83
     সহযোগিতা
    0.82
     evitando
    0.82
    ⚋
    0.80
    尽量
    0.80
     মূলত
    0.80
     owe
    0.78
    Act Density 0.052%

    No Known Activations