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

    Neuronpedia

    INDEX
    Explanations

    null safety + class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     производства
    0.48
    elerine
    0.44
    olean
    0.43
    することにより
    0.41
    enean
    0.40
     যখন
    0.40
    when
    0.39
     catered
    0.39
    ilmesi
    0.38
    érm
    0.38
    POSITIVE LOGITS
     wake
    0.39
     Wake
    0.37
     etn
    0.37
    Wake
    0.36
    稗
    0.35
    食
    0.35
    Class
    0.34
    ]`
    0.34
    ³)
    0.34
     વિસ્ત
    0.34
    Act Density 0.000%

    No Known Activations