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

    Neuronpedia

    INDEX
    Explanations

    magazine` `cover` `rocket` `

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    auks
    0.50
    শ
    0.50
    ärten
    0.46
    ನೇ
    0.46
    以上
    0.44
    近平
    0.44
    ijas
    0.43
    arkhand
    0.43
     TNumber
    0.43
    ytte
    0.43
    POSITIVE LOGITS
    o
    0.49
    6
    0.49
    Dent
    0.48
    c
    0.46
    B
    0.46
    ecode
    0.45
    p
    0.45
     l
    0.45
    volved
    0.44
    often
    0.44
    Act Density 0.001%

    No Known Activations