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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MMdd
    -0.06
    ılıp
    -0.06
    moil
    -0.06
     haline
    -0.06
     века
    -0.06
    chemical
    -0.06
    进行
    -0.06
    Fonts
    -0.06
    責
    -0.06
    "go
    -0.06
    POSITIVE LOGITS
     Enumeration
    0.07
    سمبر
    0.06
     lobbying
    0.06
    	REG
    0.06
    zept
    0.06
    .neg
    0.06
    .Measure
    0.06
     Loki
    0.06
     trolling
    0.06
     Serve
    0.06
    Act Density 0.000%

    No Known Activations