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

    Neuronpedia

    INDEX
    Explanations

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pass
    0.47
     getline
    0.47
     Semicon
    0.41
    𒁍
    0.41
    PASS
    0.40
    પાસ
    0.40
     edgecolor
    0.40
    궬
    0.40
     passivation
    0.39
     पासवान
    0.39
    POSITIVE LOGITS
    note
    0.43
     note
    0.42
    unas
    0.39
     Secretariat
    0.39
    oran
    0.38
    Note
    0.38
     incomplete
    0.37
     Reliable
    0.37
    Verify
    0.37
    self
    0.36
    Act Density 0.001%

    No Known Activations