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

    Neuronpedia

    INDEX
    Explanations

    Turned on/enabled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elon
    -0.09
    -frequency
    -0.08
    宜
    -0.07
     jistě
    -0.07
    ーパー
    -0.07
    (ids
    -0.06
    _DELTA
    -0.06
    ências
    -0.06
     sermon
    -0.06
    _strip
    -0.06
    POSITIVE LOGITS
     marching
    0.07
    ilha
    0.06
    enumerator
    0.06
     ','.
    0.05
    Fully
    0.05
     useStyles
    0.05
     Scalars
    0.05
     öld
    0.05
     option
    0.05
    �
    0.05
    Act Density 0.032%

    No Known Activations