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

    Neuronpedia

    INDEX
    Explanations

    ai

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    254
    -0.07
     choke
    -0.07
     м
    -0.07
    恐
    -0.06
    _configure
    -0.06
     有
    -0.06
    vanced
    -0.06
     Ingen
    -0.06
     luder
    -0.06
    .forChild
    -0.06
    POSITIVE LOGITS
     ai
    0.10
     �
    0.07
     irrit
    0.07
     нужно
    0.07
     Aqu
    0.07
     thải
    0.07
     irritating
    0.07
     Atlas
    0.06
     مدل
    0.06
     últimos
    0.06
    Act Density 0.003%

    No Known Activations