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

    Neuronpedia

    INDEX
    Explanations

    Initial conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wicked
    -0.06
    сті
    -0.06
    _upper
    -0.06
    /arch
    -0.06
    ra
    -0.06
    ghost
    -0.06
     throughput
    -0.06
     newNode
    -0.06
    [w
    -0.06
     сохран
    -0.06
    POSITIVE LOGITS
     ResourceType
    0.07
     possível
    0.07
     Cumhurbaşkanı
    0.06
     CSV
    0.06
    特
    0.06
    ,’’
    0.06
     Roberts
    0.06
     Carnival
    0.06
    änn
    0.06
     Als
    0.06
    Act Density 0.157%

    No Known Activations