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

    Neuronpedia

    INDEX
    Explanations

    software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Presence
    -0.07
     valid
    -0.06
     Registry
    -0.06
    _skip
    -0.06
    Warn
    -0.06
     geçerli
    -0.06
    _project
    -0.06
    归
    -0.06
    _goal
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
     medications
    0.07
    rozen
    0.06
    lua
    0.06
    的情
    0.06
     femin
    0.06
     helpful
    0.06
     elektronik
    0.06
     Dost
    0.06
    inished
    0.06
     komplex
    0.06
    Act Density 0.002%

    No Known Activations