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

    Neuronpedia

    INDEX
    Explanations

    Issue/request reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Game
    -0.08
    orris
    -0.07
    '))↵↵
    -0.07
     berlin
    -0.06
    German
    -0.06
    エル
    -0.06
     households
    -0.06
    ellation
    -0.06
    甚
    -0.06
    amel
    -0.06
    POSITIVE LOGITS
    .PR
    0.07
    _dw
    0.06
    (mysql
    0.06
     Inspector
    0.06
    .global
    0.06
     Trou
    0.06
     authDomain
    0.06
     AAA
    0.06
     Lou
    0.06
     соци
    0.06
    Act Density 0.010%

    No Known Activations