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

    Neuronpedia

    INDEX
    Explanations

    dinner, sex, or camping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.53
    s
    0.43
    ۰
    0.40
    narr
    0.40
    en
    0.39
    br
    0.39
    b
    0.39
    G
    0.39
    us
    0.39
    W
    0.38
    POSITIVE LOGITS
     tonight
    0.49
     at
    0.45
     tại
    0.45
     sessions
    0.44
    ជាមួយ
    0.43
    ceğine
    0.42
    였
    0.42
    ശേഷം
    0.42
     рук
    0.41
     অভ্যাস
    0.41
    Act Density 0.109%

    No Known Activations