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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    };*/
    -0.58
    })).
    -0.53
     adalah
    -0.52
    hoda
    -0.50
    voyance
    -0.49
    торая
    -0.49
     кӀ
    -0.49
    子は
    -0.48
    ("")]
    -0.48
    جوم
    -0.48
    POSITIVE LOGITS
     that
    0.93
     his
    0.87
     my
    0.81
     her
    0.80
     their
    0.75
    OGND
    0.75
     this
    0.69
     the
    0.68
    ViewImports
    0.67
    RectangleBorder
    0.65
    Act Density 0.000%

    No Known Activations