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

    Neuronpedia

    INDEX
    Explanations

    =>

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Clients
    -0.07
     nouns
    -0.07
    蓝
    -0.06
    _verification
    -0.06
     separ
    -0.06
     legend
    -0.06
    	class
    -0.06
     Adams
    -0.06
     IPs
    -0.06
    email
    -0.06
    POSITIVE LOGITS
     apartheid
    0.07
     collectively
    0.06
     JSBracketAccess
    0.06
    ательно
    0.06
    upuncture
    0.06
    γκε
    0.06
     申博
    0.06
    .ReadToEnd
    0.06
    โท
    0.06
    tos
    0.06
    Act Density 0.002%

    No Known Activations