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

    Neuronpedia

    INDEX
    Explanations

    treasure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     μο
    -0.07
    퓨
    -0.07
     důvodu
    -0.07
    اهش
    -0.06
     불
    -0.06
    ミュ
    -0.06
    という
    -0.06
    兹
    -0.06
     summoned
    -0.06
    손
    -0.06
    POSITIVE LOGITS
     registr
    0.07
    atabase
    0.07
     expectancy
    0.07
     database
    0.07
     Pluto
    0.07
    !↵
    0.06
    _reg
    0.06
    .↵
    0.06
     nervous
    0.06
     Banks
    0.06
    Act Density 0.014%

    No Known Activations