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

    Neuronpedia

    INDEX
    Explanations

    #error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    核心技术
    -0.08
    Knight
    -0.07
     Set
    -0.07
    ListNode
    -0.07
    驻村
    -0.07
     dez
    -0.07
     Target
    -0.07
    紫
    -0.06
    完结
    -0.06
     wrap
    -0.06
    POSITIVE LOGITS
     witty
    0.08
     windshield
    0.08
     cambios
    0.07
    _os
    0.07
    oğlu
    0.07
    volução
    0.07
     JPEG
    0.07
    (GET
    0.07
     כמעט
    0.07
    /foo
    0.06
    Act Density 0.000%

    No Known Activations