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

    Neuronpedia

    INDEX
    Explanations

    identifying a need for something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ってました
    -1.73
     aviones
    -1.65
    来自于
    -1.63
    కర్య
    -1.63
     końca
    -1.61
     utilizadas
    -1.58
    -1.57
    tonsoft
    -1.52
    ânsito
    -1.52
     helicópter
    -1.51
    POSITIVE LOGITS
     a
    2.25
    d
    1.70
    am
    1.65
    n
    1.59
    t
    1.53
    la
    1.47
    和
    1.43
    a
    1.38
    ak
    1.34
    as
    1.34
    Act Density 0.021%

    No Known Activations