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

    Neuronpedia

    INDEX
    Explanations

    harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ръ
    0.49
    股东
    0.45
     படத்தை
    0.45
    пление
    0.44
    ጧ
    0.42
     иллюстра
    0.41
     shareholders
    0.41
    vening
    0.41
     мозга
    0.40
    entials
    0.40
    POSITIVE LOGITS
     Wies
    0.40
     resta
    0.39
     Grenzen
    0.39
     xm
    0.38
     transluc
    0.38
     assessment
    0.37
     Spectral
    0.37
     জ
    0.37
     emas
    0.37
     évaluation
    0.37
    Act Density 11.183%

    No Known Activations