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

    Neuronpedia

    INDEX
    Explanations

    satisfy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fusion
    -0.07
     Her
    -0.07
     Oops
    -0.07
    Rem
    -0.07
    瓶
    -0.06
    .staff
    -0.06
    css
    -0.06
    CAM
    -0.06
    631
    -0.06
    Powered
    -0.06
    POSITIVE LOGITS
     ท
    0.07
     consultancy
    0.06
    してる
    0.06
    ">'.
    0.06
     Accred
    0.06
    38
    0.06
     china
    0.06
    andise
    0.06
    PLOY
    0.06
    žel
    0.06
    Act Density 0.134%

    No Known Activations