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

    Neuronpedia

    INDEX
    Explanations

    Good morning, break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tekn
    0.40
    ethod
    0.38
    lde
    0.38
    unctional
    0.38
    itte
    0.37
    ote
    0.37
    lar
    0.36
    ickness
    0.36
    oulders
    0.36
    ief
    0.35
    POSITIVE LOGITS
     TRS
    0.48
     pur
    0.43
     TEA
    0.43
     프랑
    0.41
    نر
    0.41
     epist
    0.40
     MBP
    0.39
    idcar
    0.39
    ್ಯೂ
    0.38
     europea
    0.38
    Act Density 0.000%

    No Known Activations