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

    Neuronpedia

    INDEX
    Explanations

    pricing and consensus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     out
    0.63
     se
    0.55
     site
    0.54
     that
    0.51
     que
    0.50
     our
    0.48
     из
    0.48
     indigenous
    0.48
     SITE
    0.48
     после
    0.48
    POSITIVE LOGITS
    OrCallback
    0.47
    ᅣ
    0.46
    horizontal
    0.46
    文件夹
    0.46
    HORIZONTAL
    0.45
    敏
    0.45
    Benzyl
    0.45
    𝒸
    0.44
    Visualization
    0.44
    oč
    0.44
    Act Density 0.007%

    No Known Activations