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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Дем
    -0.06
     authorization
    -0.06
     июня
    -0.06
     remedies
    -0.06
     Soldier
    -0.05
    veç
    -0.05
     Stamina
    -0.05
    Rank
    -0.05
     Bench
    -0.05
     imperial
    -0.05
    POSITIVE LOGITS
    /cpu
    0.07
    })
    0.07
    ,top
    0.07
    .BindingSource
    0.06
    ikon
    0.06
     verr
    0.06
     menos
    0.06
    LENGTH
    0.06
    ّل
    0.06
    论坛
    0.06
    Act Density 0.000%

    No Known Activations