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

    Neuronpedia

    INDEX
    Explanations

    Trail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bosses
    -0.07
     -->↵↵↵
    -0.07
     refurbished
    -0.07
    238
    -0.06
    _bindings
    -0.06
    /Set
    -0.06
     scrape
    -0.06
     Modifier
    -0.06
     positively
    -0.06
     Legs
    -0.06
    POSITIVE LOGITS
     Trail
    0.12
     trail
    0.09
    Trail
    0.07
    AL
    0.07
     삼
    0.07
     trails
    0.07
    ULT
    0.07
    ,cv
    0.06
    것
    0.06
    .atom
    0.06
    Act Density 0.005%

    No Known Activations