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

    Neuronpedia

    INDEX
    Explanations

    foreign language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    0.70
     I
    0.61
     is
    0.60
    因為
    0.56
     før
    0.54
    因为
    0.52
     vì
    0.51
    সীম
    0.51
     fordi
    0.50
    iscope
    0.50
    POSITIVE LOGITS
    ak
    0.72
    ższej
    0.71
     теркәлүсез
    0.66
     ak
    0.64
    achd
    0.64
    ße
    0.64
     grandsons
    0.62
    となった
    0.61
     уйнагыз
    0.61
     sangu
    0.61
    Act Density 0.095%

    No Known Activations