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

    Neuronpedia

    INDEX
    Explanations

    requires or depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alarını
    0.49
    ütfen
    0.46
    ajući
    0.46
    aménagement
    0.45
    ades
    0.44
    ằ
    0.44
     podej
    0.44
     vardı
    0.43
     měl
    0.42
    前来
    0.42
    POSITIVE LOGITS
     Debye
    0.43
     यदि
    0.42
     activar
    0.40
     kN
    0.39
    如果在
    0.38
     theorems
    0.38
     any
    0.38
     homologous
    0.38
     tiller
    0.38
     Corollary
    0.37
    Act Density 0.006%

    No Known Activations