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

    Neuronpedia

    INDEX
    Explanations

    Ana

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Parm
    -0.07
     unordered
    -0.07
    Jerry
    -0.07
    vince
    -0.06
    Resolver
    -0.06
    缱
    -0.06
    쬬
    -0.06
    ﯟ
    -0.06
    erset
    -0.06
    쑹
    -0.06
    POSITIVE LOGITS
     ana
    0.09
     /\
    0.08
     +%
    0.08
     lac
    0.07
     patched
    0.07
     Wildcats
    0.07
    ای
    0.07
     **)&
    0.07
    选手
    0.07
    َا
    0.07
    Act Density 0.005%

    No Known Activations