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

    Neuronpedia

    INDEX
    Explanations

    no or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    racting
    0.28
    ;
    0.27
     აქვს
    0.26
     avendo
    0.26
     Whether
    0.25
    に入れて
    0.24
    }
    0.24
    owns
    0.24
    เอง
    0.23
    esque
    0.23
    POSITIVE LOGITS
     plenty
    0.56
     no
    0.46
     uncertainty
    0.45
     considerable
    0.41
     ample
    0.40
     lots
    0.40
     nothing
    0.40
     confusion
    0.39
     keine
    0.38
     tons
    0.37
    Act Density 0.049%

    No Known Activations