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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    embre
    -0.07
    major
    -0.07
     zim
    -0.07
     zám
    -0.06
     skipped
    -0.06
     decid
    -0.06
     Mitarbeiter
    -0.06
    ющей
    -0.06
     via
    -0.06
    Thông
    -0.06
    POSITIVE LOGITS
    ,H
    0.07
     disproportion
    0.07
    _journal
    0.06
    _is
    0.06
    _WIDTH
    0.06
    PTION
    0.06
    .activation
    0.06
    _lifetime
    0.06
     documenting
    0.06
     verir
    0.06
    Act Density 0.030%

    No Known Activations