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

    Neuronpedia

    INDEX
    Explanations

    to be reckoned with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aira
    -0.11
    ikit
    -0.10
    zia
    -0.09
    /fw
    -0.09
    placements
    -0.09
    èħ
    -0.09
    zek
    -0.08
    ãĥĭãĤ¢
    -0.08
    vant
    -0.08
    itsu
    -0.08
    POSITIVE LOGITS
     reck
    0.29
     reckon
    0.24
    reck
    0.23
     force
    0.16
     behold
    0.15
     trif
    0.14
     feared
    0.13
     recon
    0.12
     trem
    0.11
     Guth
    0.11
    Act Density 0.023%

    No Known Activations