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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    configured
    -0.07
     phần
    -0.06
    冒
    -0.06
    .Solid
    -0.06
    -phone
    -0.06
    .self
    -0.06
     demi
    -0.06
    achts
    -0.06
     �
    -0.06
     filthy
    -0.06
    POSITIVE LOGITS
    ีว
    0.07
    (m
    0.07
     Response
    0.07
     VP
    0.07
     Representative
    0.06
    [state
    0.06
    solete
    0.06
     ASTM
    0.06
    anyak
    0.06
    $res
    0.06
    Act Density 0.051%

    No Known Activations