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
     flo
    -0.07
    XC
    -0.07
    ByteBuffer
    -0.07
    restore
    -0.07
    ディ
    -0.07
     homophobic
    -0.06
     Rd
    -0.06
    -zero
    -0.06
     bloque
    -0.06
    _company
    -0.06
    POSITIVE LOGITS
     Hitch
    0.07
    actics
    0.06
     ]}↵
    0.06
    drawing
    0.06
     angry
    0.06
    [G
    0.06
    ->[
    0.06
    posable
    0.06
     medios
    0.06
     environmentally
    0.06
    Act Density 0.006%

    No Known Activations