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

    Neuronpedia

    INDEX
    Explanations

    bass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Create
    -0.08
    .↵↵↵↵↵
    -0.07
    Elim
    -0.07
    .portal
    -0.07
    缔
    -0.07
    Extreme
    -0.07
     producing
    -0.06
     specifying
    -0.06
    ARE
    -0.06
    切入
    -0.06
    POSITIVE LOGITS
    สถ
    0.07
    YPRE
    0.07
    发现问题
    0.07
     Platz
    0.07
     الطل
    0.07
     bass
    0.07
    [::-
    0.07
     pollution
    0.07
    _act
    0.07
    풀
    0.07
    Act Density 0.003%

    No Known Activations