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

    Neuronpedia

    INDEX
    Explanations

    es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deadline
    -0.07
     simul
    -0.07
    itlement
    -0.07
     tourist
    -0.07
    Tools
    -0.07
     passwords
    -0.07
    ただし
    -0.07
    modelo
    -0.07
    交通运输
    -0.07
     Sports
    -0.07
    POSITIVE LOGITS
     меня
    0.07
     тебе
    0.07
     Divide
    0.07
    )

↵
    0.07
    𝙚
    0.07
    𝘿
    0.07
     ст
    0.07
    ﯼ
    0.07
    енно
    0.06
    =d
    0.06
    Act Density 0.001%

    No Known Activations