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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     morg
    -0.08
    AMS
    -0.07
     agam
    -0.07
     pongo
    -0.07
     maso
    -0.07
    Clas
    -0.07
    epis
    -0.07
    怎么办
    -0.07
     죽
    -0.07
     beyn
    -0.07
    POSITIVE LOGITS
     magnitude
    0.11
     dosage
    0.10
     doses
    0.09
    Magnitude
    0.09
     increments
    0.09
     воздействия
    0.09
     Cosmetic
    0.09
     amounts
    0.08
    betrag
    0.08
     offsets
    0.08
    Act Density 0.054%

    No Known Activations