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

    Neuronpedia

    INDEX
    Explanations

    concept and idea definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的
    0.43
     school
    0.42
     graded
    0.42
     considering
    0.41
     subscription
    0.41
     amputation
    0.40
     Considering
    0.39
     meta
    0.39
     W
    0.39
     short
    0.39
    POSITIVE LOGITS
    సాగ
    0.51
     遊ん
    0.48
     CtApp
    0.47
    ódigo
    0.44
     書い
    0.44
     kritis
    0.44
     Miłos
    0.44
    uchtigkeit
    0.43
     starke
    0.43
    tAux
    0.43
    Act Density 0.000%

    No Known Activations