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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _qty
    -0.07
    _ter
    -0.07
     Nazis
    -0.06
    _BACKEND
    -0.06
    ...)↵
    -0.06
     ait
    -0.06
    Fail
    -0.06
     welcomes
    -0.06
    �
    -0.06
     firstly
    -0.06
    POSITIVE LOGITS
    ographic
    0.08
    ogg
    0.06
     в
    0.06
     Dt
    0.06
     configuration
    0.06
     Derm
    0.06
    eras
    0.06
     Dysfunction
    0.06
     dní
    0.06
     REGISTER
    0.06
    Act Density 0.025%

    No Known Activations