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

    Neuronpedia

    INDEX
    Explanations

    bit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (/
    -0.07
    Answer
    -0.07
     contracted
    -0.06
    Writer
    -0.06
    aniu
    -0.06
    Hidden
    -0.06
    ï
    -0.06
    用
    -0.06
    036
    -0.06
     numeral
    -0.06
    POSITIVE LOGITS
    Fact
    0.07
     Simpl
    0.07
     serge
    0.06
     eldest
    0.06
     climb
    0.06
     مر
    0.06
    :NS
    0.06
    .ReadInt
    0.06
     花
    0.06
    ову
    0.06
    Act Density 0.026%

    No Known Activations