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

    Neuronpedia

    INDEX
    Explanations

    remotely activate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anter
    0.53
    éci
    0.50
    គ្
    0.50
    leme
    0.49
    da
    0.49
    orec
    0.49
    anting
    0.46
    villa
    0.46
    embra
    0.46
     resolución
    0.46
    POSITIVE LOGITS
     badass
    0.43
     Louisiana
    0.43
     Kuk
    0.42
     poker
    0.41
     Cajun
    0.41
     Vietnamese
    0.40
     Blunt
    0.38
    투자
    0.38
     Needle
    0.38
     childlike
    0.38
    Act Density 0.000%

    No Known Activations