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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dis
    -0.07
     isEqual
    -0.06
    >We
    -0.06
    Wir
    -0.06
     deployment
    -0.06
     now
    -0.06
     respondents
    -0.06
     coming
    -0.06
    448
    -0.06
    Iso
    -0.06
    POSITIVE LOGITS
    ublice
    0.07
     under
    0.07
    vale
    0.06
    (:,:,
    0.06
    BY
    0.06
     OF
    0.06
    neath
    0.06
    って
    0.06
     beside
    0.06
    Under
    0.06
    Act Density 0.352%

    No Known Activations