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

    Neuronpedia

    INDEX
    Explanations

    in, with, within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.67
     want
    0.57
    bs
    0.54
    I
    0.54
     ơi
    0.50
     voulez
    0.50
    ug
    0.50
    gh
    0.49
     conceive
    0.49
    Q
    0.47
    POSITIVE LOGITS
     Chinatown
    0.63
     Halloween
    0.57
     lingerie
    0.57
     Silverstone
    0.57
    једина
    0.56
     Premiere
    0.56
     România
    0.56
    órias
    0.56
    孖
    0.55
     weekend
    0.55
    Act Density 0.000%

    No Known Activations