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

    Neuronpedia

    INDEX
    Explanations

    questions, altitude, investing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.48
     EXPER
    0.46
     Astronomy
    0.44
     Biodiversity
    0.44
     Research
    0.43
     Environmental
    0.43
    在
    0.41
     met
    0.40
    amarca
    0.40
     Prevent
    0.40
    POSITIVE LOGITS
    sadquotes
    0.56
     sadistic
    0.51
     ー
    0.50
     syphilit
    0.50
     JI
    0.50
    ینڈ
    0.49
    childComplexity
    0.49
     ಸ್
    0.48
     sobbing
    0.48
     counterfeit
    0.47
    Act Density 0.002%

    No Known Activations