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

    Neuronpedia

    INDEX
    Explanations

    know whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entrap
    0.42
    assel
    0.40
     Giveen
    0.36
     Casey
    0.36
     nutr
    0.36
     assault
    0.35
     trapping
    0.35
     setDefault
    0.35
     improvisation
    0.35
     participate
    0.35
    POSITIVE LOGITS
    том
    0.43
    POM
    0.42
    vär
    0.42
    POT
    0.41
    ติก
    0.40
    ürn
    0.40
    Vor
    0.40
    을
    0.40
    TRE
    0.40
    bure
    0.40
    Act Density 0.001%

    No Known Activations