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

    Neuronpedia

    INDEX
    Explanations

    literacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Team
    -0.07
    zoom
    -0.07
    _MODAL
    -0.07
     支
    -0.06
    .move
    -0.06
    absolute
    -0.06
     zz
    -0.06
    집
    -0.06
     KING
    -0.06
     resisting
    -0.06
    POSITIVE LOGITS
    (parcel
    0.06
    LF
    0.06
    μι
    0.06
     Cycl
    0.06
    rics
    0.06
    iệc
    0.06
    userManager
    0.06
    AGER
    0.06
    ATED
    0.06
     ihtiyaç
    0.06
    Act Density 0.007%

    No Known Activations