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

    Neuronpedia

    INDEX
    Explanations

    parentheses and curly braces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhằm
    -0.06
     смесь
    -0.06
    ickými
    -0.06
     founders
    -0.06
     Filipino
    -0.06
    -he
    -0.06
    _msgs
    -0.06
    ีเด
    -0.06
     Jama
    -0.06
     Hogan
    -0.06
    POSITIVE LOGITS
     affordability
    0.07
     Rodriguez
    0.06
    прав
    0.06
    _INTR
    0.06
    ธรรม
    0.06
     خبر
    0.06
    amble
    0.06
    \application
    0.06
     Nay
    0.06
     Sov
    0.06
    Act Density 0.011%

    No Known Activations