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

    Neuronpedia

    INDEX
    Explanations

    problem-solving skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sehat
    0.57
    S
    0.55
    Bus
    0.54
    乗
    0.53
    R
    0.52
    Т
    0.52
    NR
    0.52
    Methyl
    0.51
     Biodiversity
    0.51
    HUS
    0.51
    POSITIVE LOGITS
    ]
    0.69
     possibile
    0.64
    òa
    0.62
     gioc
    0.62
     domenica
    0.61
     comforted
    0.61
    eri
    0.59
    ên
    0.58
    ji
    0.57
     کوډ
    0.57
    Act Density 0.024%

    No Known Activations