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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cent
    -0.07
    =True
    -0.06
    Howard
    -0.06
     Bobby
    -0.06
    surname
    -0.06
     Neck
    -0.06
     htmlentities
    -0.06
     koruy
    -0.06
     Jazeera
    -0.06
     Dwight
    -0.06
    POSITIVE LOGITS
     plenty
    0.07
     terminals
    0.07
     AVAILABLE
    0.06
    是个
    0.06
     للس
    0.06
     alteration
    0.06
    ↵    ↵    ↵
    0.06
     experimenting
    0.06
    clinical
    0.06
     roce
    0.06
    Act Density 0.061%

    No Known Activations