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

    Neuronpedia

    INDEX
    Explanations

    enticement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oglob
    -0.07
    ительным
    -0.07
    StorageSync
    -0.07
     axis
    -0.07
    ahat
    -0.06
    κή
    -0.06
    setState
    -0.06
    競
    -0.06
    mployee
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     lure
    0.07
    441
    0.06
    (sig
    0.06
     Either
    0.06
    (IF
    0.06
     enticing
    0.06
    scoped
    0.06
    	Create
    0.06
    ?????
    0.06
     attracting
    0.06
    Act Density 0.006%

    No Known Activations