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

    Neuronpedia

    INDEX
    Explanations

    daily life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estimés
    -0.62
     huiles
    -0.58
     okuyayım
    -0.58
     típus
    -0.56
     frequência
    -0.54
     épaules
    -0.54
     sièges
    -0.52
     pouvoirs
    -0.52
     dizaines
    -0.52
    CreateModel
    -0.51
    POSITIVE LOGITS
    VersionUID
    0.59
     Roskov
    0.55
    èdia
    0.55
     canin
    0.54
    下载附件
    0.53
    Hochspringen
    0.53
     chores
    0.51
    ệc
    0.49
     detergents
    0.49
    BagConstraints
    0.48
    Act Density 0.005%

    No Known Activations