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

    Neuronpedia

    INDEX
    Explanations

    ($)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hole
    -0.07
    BigInt
    -0.07
    erokee
    -0.07
     objectively
    -0.06
    _ALIGNMENT
    -0.06
    	range
    -0.06
     consistently
    -0.06
    _integer
    -0.06
     infix
    -0.06
     майбут
    -0.06
    POSITIVE LOGITS
    namespace
    0.07
    _Max
    0.07
    .WebControls
    0.07
    odata
    0.06
     그녀는
    0.06
     �
    0.06
     얼
    0.06
    [new
    0.06
    _minor
    0.06
    ريب
    0.06
    Act Density 0.007%

    No Known Activations