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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -imm
    -0.07
     Cold
    -0.07
     ipv
    -0.07
    ah
    -0.07
    />
    -0.06
     attorneys
    -0.06
     powerless
    -0.06
    ﾏ
    -0.06
    pain
    -0.06
    öl
    -0.06
    POSITIVE LOGITS
    ዶ
    0.07
    Ë
    0.07
    _NEED
    0.07
     highlights
    0.07
    Initialization
    0.07
    ്�
    0.07
    Courses
    0.07
    俶
    0.07
    �
    0.06
    .RegularExpressions
    0.06
    Act Density 0.023%

    No Known Activations