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

    Neuronpedia

    INDEX
    Explanations

    semicolon followed by temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IDENTIAL
    0.40
    密
    0.39
    ர்களே
    0.38
    pertensive
    0.36
    VIDOR
    0.36
    atai
    0.36
    idoscope
    0.36
    ented
    0.35
     hopefully
    0.35
     endurance
    0.35
    POSITIVE LOGITS
    пра
    0.44
     PRA
    0.44
     rs
    0.43
     пра
    0.42
     Pra
    0.41
    %");
    0.40
    pra
    0.39
     Prairie
    0.38
    Пра
    0.38
    %;
    0.38
    Act Density 0.003%

    No Known Activations