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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manager
    -0.07
    Mex
    -0.07
     Shakespeare
    -0.07
     Queens
    -0.06
    orn
    -0.06
     prostitution
    -0.06
    miyor
    -0.06
    .setColor
    -0.06
    MED
    -0.06
    isol
    -0.06
    POSITIVE LOGITS
    utive
    0.07
    _friends
    0.07
    coverage
    0.06
    	freopen
    0.06
    FFE
    0.06
     retrofit
    0.06
    /Test
    0.06
     concepts
    0.06
    eus
    0.06
    (accounts
    0.06
    Act Density 0.039%

    No Known Activations