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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deniz
    -0.08
     livre
    -0.07
     vegas
    -0.06
     grenades
    -0.06
     AREA
    -0.06
     Evangel
    -0.06
     cidade
    -0.06
    _binding
    -0.06
     valu
    -0.06
     Crescent
    -0.06
    POSITIVE LOGITS
    Shortcut
    0.07
     ==↵
    0.06
    :"",↵
    0.06
    LOCK
    0.06
    MD
    0.06
    acing
    0.06
     Cold
    0.06
    Primary
    0.06
    inish
    0.06
    auen
    0.06
    Act Density 0.004%

    No Known Activations