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

    Neuronpedia

    INDEX
    Explanations

    tbsp followed by oil or sauce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mente
    0.81
     هی
    0.81
     gerne
    0.79
     tä
    0.78
     experiências
    0.76
     das
    0.75
     ficción
    0.75
     સારી
    0.74
     encima
    0.74
    på
    0.74
    POSITIVE LOGITS
    Floating
    0.94
     Floating
    0.92
    Environmental
    0.91
     Environmental
    0.89
     escorted
    0.89
     floating
    0.86
     stepped
    0.84
     microphone
    0.83
     foothold
    0.82
     মহাশ
    0.82
    Act Density 0.001%

    No Known Activations