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

    Neuronpedia

    INDEX
    Explanations

    yield or output programmatic values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carolina
    0.40
    conventional
    0.39
    zerű
    0.38
    mpg
    0.37
    または
    0.37
     जिस
    0.37
     decept
    0.36
     또는
    0.36
     trick
    0.36
    Conventional
    0.35
    POSITIVE LOGITS
    同事
    0.45
     管理
    0.39
     иш
    0.38
     alk
    0.38
    浲
    0.37
     normalize
    0.36
     Secretario
    0.36
     Colle
    0.36
    Mannschaft
    0.36
     migrants
    0.35
    Act Density 0.000%

    No Known Activations