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

    Neuronpedia

    INDEX
    Explanations

    distribution distrib

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സ്ഥല
    0.68
    ຜະລິດຕ
    0.64
    ۹
    0.59
     Люди
    0.58
     Кара
    0.57
     أحمد
    0.57
    <unused215>
    0.57
    cdZ
    0.57
    っている
    0.57
    <unused975>
    0.57
    POSITIVE LOGITS
    ies
    0.69
    S
    0.65
     this
    0.61
    い
    0.59
     that
    0.59
    er
    0.57
     deployments
    0.57
    ifier
    0.57
    با
    0.57
     say
    0.56
    Act Density 0.000%

    No Known Activations