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

    Neuronpedia

    INDEX
    Explanations

    blueberry lavender

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     domicilio
    0.42
     подозре
    0.40
     valour
    0.39
    udges
    0.38
    HintPath
    0.38
     prestige
    0.38
     unproductive
    0.38
     звуча
    0.37
     deont
    0.37
     revenge
    0.37
    POSITIVE LOGITS
     scut
    0.46
    ፒ
    0.46
    র্ব
    0.45
    λάβ
    0.43
    уро
    0.42
    ј
    0.42
    爌
    0.41
    亰
    0.41
    frameN
    0.40
    乌
    0.40
    Act Density 0.001%

    No Known Activations