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

    Neuronpedia

    INDEX
    Explanations

    code and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
                                        ↵
    -0.08
     Simple
    -0.07
     Ole
    -0.07
    	startActivity
    -0.07
     Truth
    -0.07
    ísticas
    -0.07
     Aleks
    -0.07
     Artikel
    -0.07
     activating
    -0.07
    单项
    -0.07
    POSITIVE LOGITS
     nhiêu
    0.08
     collisions
    0.07
    إجر
    0.07
    山路
    0.07
    uil
    0.07
    ymes
    0.07
    𝑓
    0.07
    dé
    0.06
    💒
    0.06
     دائ
    0.06
    Act Density 0.679%

    No Known Activations