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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    工程
    -0.07
     incel
    -0.07
    indeki
    -0.07
    發展
    -0.06
    -focused
    -0.06
     Youtube
    -0.06
     guild
    -0.06
    .setTextColor
    -0.06
    CallCheck
    -0.06
    toBeFalsy
    -0.06
    POSITIVE LOGITS
    …it
    0.06
     REGISTER
    0.06
    (force
    0.06
     tabletop
    0.06
     INTERN
    0.06
     loved
    0.06
    ssue
    0.06
     say
    0.06
     Gros
    0.06
    OLUM
    0.06
    Act Density 0.100%

    No Known Activations