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

    Neuronpedia

    INDEX
    Explanations

    clears throat, issues, depends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    F
    0.50
    le
    0.48
    Ben
    0.45
    Camping
    0.44
    at
    0.43
    Peg
    0.43
    Agriculture
    0.43
     adopter
    0.43
    論
    0.42
    ต
    0.42
    POSITIVE LOGITS
     Consultado
    0.52
     помогут
    0.52
     têm
    0.50
     \%)$
    0.49
     позволяют
    0.49
    жаться
    0.48
     često
    0.47
    чее
    0.47
     présentent
    0.47
     suj
    0.47
    Act Density 0.002%

    No Known Activations