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

    Neuronpedia

    INDEX
    Explanations

    atomic spin/magnetism/polarization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è¿IJæ°Ķ
    -0.28
    ä¿Ŀéļľ
    -0.27
    çijĻ
    -0.27
    åħ³éŨ
    -0.27
    åŀĽ
    -0.26
    oins
    -0.26
    unct
    -0.26
    unto
    -0.26
    RICT
    -0.25
    orst
    -0.25
    POSITIVE LOGITS
    ä¸Ńå¤ĸ
    0.28
    缦
    0.25
     reb
    0.25
     Express
    0.25
    airy
    0.25
     Reb
    0.25
     spe
    0.25
     deb
    0.24
    ingerprint
    0.24
     forg
    0.24
    Act Density 0.614%

    No Known Activations