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

    Neuronpedia

    INDEX
    Explanations

    Statistics in research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     плат
    -0.07
    -tax
    -0.06
    ματο
    -0.06
     Norton
    -0.06
     MMI
    -0.06
     потреб
    -0.06
     venta
    -0.06
     possono
    -0.06
    -many
    -0.06
     переход
    -0.06
    POSITIVE LOGITS
     express
    0.07
    _SSL
    0.07
    咲
    0.06
    .builder
    0.06
    ิญ
    0.06
    -bind
    0.06
     assertNotNull
    0.06
    //**↵
    0.06
    lion
    0.06
    oky
    0.06
    Act Density 0.035%

    No Known Activations