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

    Neuronpedia

    INDEX
    Explanations

    code and technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    riever
    0.57
    ensatz
    0.56
    imiento
    0.52
    ApiModel
    0.52
     Cruise
    0.52
     смог
    0.52
    fähigkeit
    0.51
    借鉴
    0.51
     ৃ
    0.51
    rave
    0.50
    POSITIVE LOGITS
     halogen
    0.66
     Harlow
    0.63
    ethylene
    0.62
     DL
    0.62
     हान
    0.61
    瑙
    0.59
     inquiry
    0.59
     fumes
    0.59
     ordin
    0.58
    ダウン
    0.58
    Act Density 0.000%

    No Known Activations