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
     Spoj
    -0.07
     Ten
    -0.06
    ़
    -0.06
     /><
    -0.06
    _DSP
    -0.06
    �
    -0.06
    Even
    -0.06
    yny
    -0.06
    Part
    -0.06
    even
    -0.06
    POSITIVE LOGITS
    대회
    0.07
     modulation
    0.06
    =========↵
    0.06
     دارد
    0.06
     armor
    0.06
     linker
    0.06
     newState
    0.06
    oppel
    0.06
    	lp
    0.06
    ."',
    0.06
    Act Density 0.000%

    No Known Activations