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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relapse
    -0.08
     steig
    -0.08
     إج
    -0.08
     الحديث
    -0.08
    疫情
    -0.08
     استمرار
    -0.07
    מל
    -0.07
     GUID
    -0.07
     kilom
    -0.07
     Conversation
    -0.07
    POSITIVE LOGITS
    权限
    0.22
     permissions
    0.19
    permissions
    0.19
    .permissions
    0.18
     permisos
    0.18
    Permissions
    0.18
    Permission
    0.18
    _permissions
    0.18
     permission
    0.17
    _PERMISSION
    0.17
    Act Density 0.015%

    No Known Activations