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

    Neuronpedia

    INDEX
    Explanations

    no or without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     approves
    0.33
    Eine
    0.32
     unable
    0.32
     hefyd
    0.32
     GIRL
    0.31
     matches
    0.31
     ASSERT
    0.31
     MEMBERS
    0.30
     AMOUNT
    0.30
     alerted
    0.30
    POSITIVE LOGITS
    NO
    0.36
     نیاز
    0.36
     tanpa
    0.35
    No
    0.34
    OB
    0.34
     نقصان
    0.34
    hass
    0.33
     compromise
    0.33
    无需
    0.33
     senza
    0.33
    Act Density 0.048%

    No Known Activations