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

    Neuronpedia

    INDEX
    Explanations

    Code and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _align
    -0.07
    ?=
    -0.07
     بلند
    -0.07
    шиб
    -0.07
    	height
    -0.07
    воз
    -0.06
    _bases
    -0.06
     idade
    -0.06
    ative
    -0.06
     helium
    -0.06
    POSITIVE LOGITS
     }}>{
    0.08
    を行
    0.06
    -Semit
    0.06
     millions
    0.06
    .↵↵↵↵↵↵↵↵↵↵
    0.06
     tự
    0.06
     ejec
    0.06
    考え
    0.06
     Regarding
    0.06
     організ
    0.05
    Act Density 0.086%

    No Known Activations