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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	contentPane
    -0.07
     に
    -0.06
     merits
    -0.06
    black
    -0.06
    hotel
    -0.06
    ertiary
    -0.06
     �
    -0.06
     pedestal
    -0.06
     vzdálen
    -0.05
    _Private
    -0.05
    POSITIVE LOGITS
     consensus
    0.08
     HELP
    0.07
    ASY
    0.07
     Fang
    0.07
     Classification
    0.07
     hl
    0.07
     Harold
    0.07
     syntax
    0.07
    STD
    0.07
    asy
    0.07
    Act Density 0.000%

    No Known Activations