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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    новид
    -0.07
     sera
    -0.07
    essages
    -0.07
     Modules
    -0.07
    (fun
    -0.07
    736
    -0.07
     realloc
    -0.06
    ElementType
    -0.06
     hjem
    -0.06
     mie
    -0.06
    POSITIVE LOGITS
     scent
    0.06
    ow
    0.06
    OW
    0.06
     sack
    0.06
    Virginia
    0.06
     mast
    0.06
    145
    0.06
    developer
    0.06
     celebrating
    0.06
    decl
    0.06
    Act Density 0.000%

    No Known Activations