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

    Neuronpedia

    INDEX
    Explanations

    AI disclaimers and services

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FD
    0.58
     Floyd
    0.54
    燧
    0.52
    Flag
    0.52
    E
    0.52
    فرنس
    0.50
    vient
    0.50
    Venus
    0.50
    Flo
    0.50
    庿
    0.49
    POSITIVE LOGITS
     ὁ
    0.50
     antiv
    0.50
    AMS
    0.49
    ams
    0.49
     AMS
    0.49
     briefs
    0.48
    metall
    0.48
     Já
    0.47
     метал
    0.47
     amma
    0.46
    Act Density 0.013%

    No Known Activations