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

    Neuronpedia

    INDEX
    Explanations

    Code and technical standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bulk
    -0.08
    罢
    -0.07
     contemplating
    -0.07
     isl
    -0.07
    เคล
    -0.07
    ()):
    -0.07
    "+↵
    -0.07
    ジョ
    -0.07
               
↵
    -0.07
    	ASSERT
    -0.07
    POSITIVE LOGITS
    dar
    0.08
    gz
    0.07
    appear
    0.07
     theoret
    0.06
    approved
    0.06
    nar
    0.06
    ologie
    0.06
     cargar
    0.06
    енный
    0.06
    婻
    0.06
    Act Density 0.005%

    No Known Activations