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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wel
    -0.07
     preschool
    -0.06
     �
    -0.06
     Surre
    -0.06
     INLINE
    -0.06
     เส
    -0.06
     Glas
    -0.06
    Tek
    -0.06
     tř
    -0.06
    _HOST
    -0.06
    POSITIVE LOGITS
    全部
    0.07
     breasts
    0.06
     inferred
    0.06
    _load
    0.06
    "><?=
    0.06
     ит
    0.06
     resorts
    0.06
    ный
    0.06
    概
    0.06
    uyền
    0.06
    Act Density 0.000%

    No Known Activations