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
     validating
    -0.08
    _INC
    -0.07
    _Pos
    -0.07
    าษ
    -0.07
    _persona
    -0.06
    cas
    -0.06
    Senha
    -0.06
    �
    -0.06
    717
    -0.06
    _char
    -0.06
    POSITIVE LOGITS
     NSNumber
    0.07
     υπηρε
    0.07
     winnings
    0.06
     дом
    0.06
    ือง
    0.06
    (jLabel
    0.06
     世界
    0.06
     GUIStyle
    0.06
    MITTED
    0.06
     NUITKA
    0.06
    Act Density 0.032%

    No Known Activations