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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gonz
    -0.07
     faith
    -0.06
     endoth
    -0.06
     FALL
    -0.06
    Camp
    -0.06
     acomp
    -0.06
    .Str
    -0.06
    official
    -0.06
    _embed
    -0.06
    .Search
    -0.06
    POSITIVE LOGITS
    Its
    0.06
    ,private
    0.06
    -Pack
    0.06
    oyal
    0.06
    ált
    0.06
    овая
    0.06
    rowing
    0.06
    .binding
    0.06
     estas
    0.06
     mongoose
    0.06
    Act Density 0.008%

    No Known Activations