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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    νας
    -0.07
     elk
    -0.07
     dirt
    -0.07
     Parties
    -0.06
     Huss
    -0.06
     працівників
    -0.06
     hind
    -0.06
     cc
    -0.06
    Member
    -0.06
    563
    -0.06
    POSITIVE LOGITS
    ifice
    0.07
    	trigger
    0.07
    scale
    0.06
    ा)
    0.06
     beide
    0.06
    기타
    0.06
    ุนายน
    0.06
     RuntimeObject
    0.06
     거의
    0.06
    insn
    0.06
    Act Density 0.295%

    No Known Activations