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

    Neuronpedia

    INDEX
    Explanations

    golf putting and Fitbit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.64
    the
    0.60
    S
    0.60
    P
    0.59
    قی
    0.58
    O
    0.57
    OL
    0.56
     Stat
    0.55
    R
    0.55
    W
    0.55
    POSITIVE LOGITS
    汅
    0.59
     duda
    0.58
    主机
    0.54
    льные
    0.53
    もり
    0.53
     DOU
    0.52
     calda
    0.52
    ForRule
    0.52
    ying
    0.51
     две
    0.51
    Act Density 0.000%

    No Known Activations