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

    Neuronpedia

    INDEX
    Explanations

    Justifying the need for something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Payload
    -0.08
    ())/
    -0.07
     valuation
    -0.06
    าป
    -0.06
     imposed
    -0.06
    Pinterest
    -0.06
    _REGION
    -0.06
    Ray
    -0.05
    _viewer
    -0.05
    적
    -0.05
    POSITIVE LOGITS
    ظٹ
    0.07
     Transparent
    0.06
     р
    0.06
    riteln
    0.06
    __[
    0.06
     فض
    0.06
    coil
    0.06
     FOUND
    0.06
     SUPER
    0.06
    řím
    0.06
    Act Density 0.053%

    No Known Activations