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

    Neuronpedia

    INDEX
    Explanations

    thought

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Σ
    -0.08
    (est
    -0.07
     justifyContent
    -0.07
    瞬间
    -0.07
    一经
    -0.07
    Sat
    -0.07
     BETWEEN
    -0.07
    Str
    -0.07
     among
    -0.07
    .setOnClickListener
    -0.07
    POSITIVE LOGITS
     Employer
    0.08
    茵
    0.07
    =head
    0.07
     uninsured
    0.07
     Designer
    0.07
    	pool
    0.07
     alcoholic
    0.07
     CP
    0.07
    发展中
    0.07
    흑
    0.07
    Act Density 0.017%

    No Known Activations