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

    Neuronpedia

    INDEX
    Explanations

    Written text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Laughs
    -0.08
     mogul
    -0.08
     לשמוע
    -0.07
     misogyn
    -0.07
    唠
    -0.07
     cola
    -0.07
     striped
    -0.07
     MEMBER
    -0.07
     disgusted
    -0.07
     culinary
    -0.07
    POSITIVE LOGITS
    ){
    0.08
     //=
    0.07
    ⇛
    0.06
    '));↵↵
    0.06
     Advances
    0.06
    Ặ
    0.06
    procedure
    0.06
    克服
    0.06
    讓
    0.06
     this
    0.06
    Act Density 0.548%

    No Known Activations