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

    Neuronpedia

    INDEX
    Explanations

    no not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾರ
    0.49
    指摘
    0.44
     받
    0.41
    ї
    0.40
    찮
    0.40
    ือ
    0.40
    クマ
    0.40
    maskedTextBox
    0.40
    収入
    0.39
    bullying
    0.39
    POSITIVE LOGITS
     bein
    0.48
     eliminate
    0.42
     jazz
    0.42
     incapable
    0.42
    !<
    0.42
     styles
    0.41
     operate
    0.41
     groovy
    0.40
     attitudes
    0.40
     अस
    0.39
    Act Density 0.045%

    No Known Activations