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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EMP
    -0.08
    inesis
    -0.07
    -upload
    -0.07
    HORT
    -0.07
    都会
    -0.07
    咍
    -0.07
    IST
    -0.07
    may
    -0.07
    firm
    -0.07
     texture
    -0.07
    POSITIVE LOGITS
     writer
    0.07
     decentral
    0.07
     Case
    0.07
    /ca
    0.06
     #-
    0.06
     Genius
    0.06
     sincere
    0.06
    .put
    0.06
     fron
    0.06
     measures
    0.06
    Act Density 0.005%

    No Known Activations