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

    Neuronpedia

    INDEX
    Explanations

    hosts and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     करोड़
    0.43
     ঘন্ট
    0.42
    buri
    0.41
    pios
    0.41
    ouilles
    0.41
    Resolved
    0.39
     milij
    0.39
    豕
    0.38
     stolet
    0.38
    dml
    0.38
    POSITIVE LOGITS
    UserManager
    0.61
     UserManager
    0.60
     Group
    0.57
     group
    0.56
     Gruppen
    0.54
     групп
    0.54
     groups
    0.52
     Groups
    0.52
     auth
    0.51
     grupo
    0.51
    Act Density 0.004%

    No Known Activations