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

    Neuronpedia

    INDEX
    Explanations

    pytorch code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stimulant
    0.38
    regar
    0.36
    renerg
    0.33
    thren
    0.31
     myof
    0.31
    метр
    0.31
    мот
    0.30
    lays
    0.30
    dun
    0.30
    сить
    0.29
    POSITIVE LOGITS
     again
    0.47
    again
    0.44
     போலவே
    0.44
     আবার
    0.39
    以外の
    0.38
     lagi
    0.38
     के
    0.38
    ैक
    0.38
     کے
    0.37
     році
    0.37
    Act Density 0.181%

    No Known Activations