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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -board
    -0.06
     facet
    -0.06
    lot
    -0.06
    -syntax
    -0.06
    jump
    -0.06
     cap
    -0.06
    .AR
    -0.06
     เค
    -0.06
     facets
    -0.06
     Neal
    -0.06
    POSITIVE LOGITS
     ini
    0.07
     estr
    0.07
    τουργ
    0.06
     tavs
    0.06
    WARDED
    0.06
     Pam
    0.06
     Tol
    0.06
    reserve
    0.06
    ordo
    0.06
    .gamma
    0.06
    Act Density 0.011%

    No Known Activations