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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MDB
    -0.06
    	show
    -0.06
     відповідаль
    -0.06
     американ
    -0.06
    .opend
    -0.06
    .effect
    -0.06
     hoạt
    -0.06
    -org
    -0.06
    (Bit
    -0.05
     Seeder
    -0.05
    POSITIVE LOGITS
    each
    0.07
    _comments
    0.07
     wilderness
    0.07
    }`↵
    0.06
    .'<
    0.06
    ！");↵
    0.06
    weigh
    0.06
     address
    0.06
     Menu
    0.06
     resets
    0.06
    Act Density 0.040%

    No Known Activations