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

    Neuronpedia

    INDEX
    Explanations

    algebraic simplification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hundred
    -0.07
    ificant
    -0.07
    プ
    -0.07
    trx
    -0.07
    oci
    -0.06
    -tag
    -0.06
    ouncements
    -0.06
    -fired
    -0.06
    ynthesis
    -0.06
    -static
    -0.06
    POSITIVE LOGITS
     premature
    0.07
    	ASSERT
    0.07
    .setRotation
    0.07
     कव
    0.06
    INS
    0.06
     apex
    0.06
     perl
    0.06
    �
    0.06
    vertising
    0.06
     gal
    0.06
    Act Density 0.003%

    No Known Activations