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

    Neuronpedia

    INDEX
    Explanations

    links, lists, or sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    铳
    0.47
     летом
    0.41
    kipun
    0.40
     стоковое
    0.40
     പിന്നീട്
    0.39
    дах
    0.39
    加以
    0.39
    transistors
    0.39
     disreg
    0.38
     antagonistic
    0.38
    POSITIVE LOGITS
     voici
    0.49
     outpouring
    0.43
     oficialmente
    0.43
     Sierra
    0.42
     lớn
    0.42
     itin
    0.41
     principales
    0.41
     Már
    0.41
    )：
    0.41
     Homecoming
    0.40
    Act Density 0.005%

    No Known Activations