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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zase
    -0.08
     этих
    -0.07
     Geek
    -0.07
    ╝
    -0.06
    وغ
    -0.06
     overt
    -0.06
     문서
    -0.06
    tour
    -0.06
     amigos
    -0.06
    userid
    -0.06
    POSITIVE LOGITS
    заб
    0.07
    .Pin
    0.06
    quence
    0.06
    	String
    0.06
    lığa
    0.06
    _ALIGN
    0.06
     Executor
    0.06
    庭
    0.06
    ава
    0.06
     virtually
    0.06
    Act Density 0.033%

    No Known Activations