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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponent
    -0.07
    loating
    -0.07
     newItem
    -0.07
    letcher
    -0.07
    jury
    -0.07
     regularization
    -0.07
     ser
    -0.06
    _disk
    -0.06
    ۲۸
    -0.06
    Unsigned
    -0.06
    POSITIVE LOGITS
    емые
    0.06
     hairst
    0.06
    �
    0.06
    etro
    0.06
     lij
    0.06
     потол
    0.06
    bad
    0.06
     Yuri
    0.06
    Tell
    0.06
    مول
    0.06
    Act Density 0.031%

    No Known Activations