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

    Neuronpedia

    INDEX
    Explanations

    equality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qint
    -0.07
     struk
    -0.07
    _MUX
    -0.06
    (layers
    -0.06
     утеп
    -0.06
    сяч
    -0.06
     tvb
    -0.06
     gsl
    -0.06
    _RSP
    -0.06
    běhu
    -0.06
    POSITIVE LOGITS
    τι
    0.06
    ลง
    0.06
     addition
    0.06
     obscured
    0.06
     implicitly
    0.06
    arranty
    0.06
     discriminatory
    0.06
    받
    0.06
    mayacak
    0.06
     přip
    0.06
    Act Density 0.006%

    No Known Activations