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

    Neuronpedia

    INDEX
    Explanations

    harmful historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mē
    0.43
     হেতু
    0.42
    iativa
    0.41
    munition
    0.41
     previsão
    0.40
     நிய
    0.40
     qualify
    0.39
     immunized
    0.39
    supportsFocus
    0.39
     disappears
    0.39
    POSITIVE LOGITS
     Mind
    0.46
    Mind
    0.42
     mind
    0.40
    すみ
    0.40
     MIND
    0.40
     gj
    0.37
    志森
    0.37
     Kuba
    0.37
     Scanning
    0.36
     Facebook
    0.36
    Act Density 0.002%

    No Known Activations