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
     Як
    -0.06
     Panel
    -0.06
    ENTIAL
    -0.06
     statements
    -0.06
     limits
    -0.06
    -turned
    -0.06
    SEA
    -0.05
     Remarks
    -0.05
     explicit
    -0.05
     ไป
    -0.05
    POSITIVE LOGITS
    :ss
    0.08
    /ayushman
    0.07
    -Encoding
    0.07
    _hold
    0.07
     hton
    0.07
    ิช
    0.07
    ayette
    0.07
    .parentNode
    0.06
     baker
    0.06
     contested
    0.06
    Act Density 0.000%

    No Known Activations