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

    Neuronpedia

    INDEX
    Explanations

    taxes and deductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    园
    -0.07
     словами
    -0.07
    府
    -0.07
     insightful
    -0.07
    志
    -0.06
    .spatial
    -0.06
     曰
    -0.06
    �
    -0.06
     Doesn
    -0.06
    质
    -0.06
    POSITIVE LOGITS
    '],
↵
    0.07
     neutr
    0.07
     Phong
    0.07
    (Command
    0.06
    avatars
    0.06
     şark
    0.06
    	UInt
    0.06
     financial
    0.06
     guar
    0.06
    \Mapping
    0.06
    Act Density 0.013%

    No Known Activations