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

    Neuronpedia

    INDEX
    Explanations

    areas and fields

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    41
    -0.07
    ===
    -0.07
    Testing
    -0.07
    Query
    -0.07
     listop
    -0.07
    _byte
    -0.07
    sphere
    -0.07
    *"
    -0.06
     stepped
    -0.06
    ську
    -0.06
    POSITIVE LOGITS
     ممن
    0.06
    .GetAll
    0.06
     NZ
    0.06
     journée
    0.06
     orchestra
    0.05
     infield
    0.05
     Mehmet
    0.05
     кож
    0.05
     也
    0.05
     MSM
    0.05
    Act Density 0.067%

    No Known Activations