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

    Neuronpedia

    INDEX
    Explanations

    easy to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $*
    0.38
     Chill
    0.34
    家长
    0.34
    ESO
    0.34
    JK
    0.33
    BUFF
    0.33
     Thu
    0.32
     &\
    0.32
    ILT
    0.32
     अभिभाव
    0.32
    POSITIVE LOGITS
    Соцмережа
    0.42
    čius
    0.41
    𝓱
    0.41
    ávat
    0.41
    পন্ন
    0.40
    Ordinate
    0.40
    ⃖
    0.40
    须
    0.39
     მან
    0.39
     distancia
    0.39
    Act Density 0.000%

    No Known Activations