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
     flow
    -0.08
     عناصر
    -0.08
    مه
    -0.08
     χαρακ
    -0.08
     sær
    -0.07
     χαρακτηρισ
    -0.07
     tailoring
    -0.07
     αντικ
    -0.07
    actér
    -0.07
     πληροφο
    -0.07
    POSITIVE LOGITS
    _hide
    0.09
    Disable
    0.08
    disabled
    0.08
    _disabled
    0.08
    terity
    0.08
    arges
    0.08
    ares
    0.08
    Category
    0.08
    Disabled
    0.08
    hub
    0.08
    Act Density 0.007%

    No Known Activations