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

    Neuronpedia

    INDEX
    Explanations

    a little goes a long way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onesian
    0.38
     ISA
    0.37
     bet
    0.37
     IVA
    0.37
    onaise
    0.36
     piscine
    0.35
     বিষয়টা
    0.35
    Թ
    0.35
    pedido
    0.35
     superconductor
    0.35
    POSITIVE LOGITS
     far
    0.86
     jauh
    0.86
     daleko
    0.81
     дале
    0.79
     lång
    0.78
     long
    0.76
     longo
    0.75
     miles
    0.74
     lejos
    0.73
     далеко
    0.73
    Act Density 0.003%

    No Known Activations