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

    Neuronpedia

    INDEX
    Explanations

    Negative contractions/words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scala
    -0.07
    .Down
    -0.06
     Blackhawks
    -0.06
     國
    -0.06
     Phot
    -0.06
     plates
    -0.06
    ("\"
    -0.06
    <Node
    -0.06
    yw
    -0.06
    @m
    -0.06
    POSITIVE LOGITS
    ุมชน
    0.07
    -blood
    0.07
     manufacture
    0.07
     wizard
    0.06
    .deb
    0.06
    ेदन
    0.06
    charger
    0.06
     sonucu
    0.06
    -II
    0.06
    (UnmanagedType
    0.06
    Act Density 0.057%

    No Known Activations