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

    Neuronpedia

    INDEX
    Explanations

    J

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іст
    -0.07
     elseif
    -0.06
    ็นท
    -0.06
     iterations
    -0.06
    یشن
    -0.06
    [Y
    -0.06
     minib
    -0.05
    	elseif
    -0.05
     реб
    -0.05
     돌아
    -0.05
    POSITIVE LOGITS
    source
    0.07
     Golden
    0.07
     reloading
    0.07
     immigration
    0.07
    turn
    0.07
     investigación
    0.07
    ")}↵
    0.07
     Womens
    0.07
    ้าห
    0.07
     clang
    0.06
    Act Density 0.000%

    No Known Activations