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

    Neuronpedia

    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    娱乐
    -0.07
     '../../
    -0.07
     az
    -0.07
     Debt
    -0.07
    	win
    -0.06
     bucket
    -0.06
     oil
    -0.06
    Sac
    -0.06
    dealloc
    -0.06
    Set
    -0.06
    POSITIVE LOGITS
    jections
    0.07
    ATING
    0.06
    iei
    0.06
    Au
    0.06
    /wait
    0.06
    γου
    0.06
     whenever
    0.06
    orang
    0.06
    )paren
    0.06
    wanted
    0.06
    Act Density 0.016%

    No Known Activations