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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initializing
    -0.06
    希腊
    -0.06
     Danny
    -0.06
     Maya
    -0.06
    III
    -0.06
    	try
    -0.06
    irates
    -0.06
    首家
    -0.06
    .jetbrains
    -0.06
     Fill
    -0.06
    POSITIVE LOGITS
     scrut
    0.07
    🍤
    0.07
    nable
    0.07
    _lead
    0.07
    指挥
    0.07
    ╘
    0.07
     schem
    0.07
    _DX
    0.07
    _mr
    0.07
    ᡴ
    0.07
    Act Density 0.027%

    No Known Activations