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

    Neuronpedia

    INDEX
    Explanations

    Function words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    postId
    -0.07
    侧
    -0.07
     secrecy
    -0.06
     provincial
    -0.06
    eea
    -0.06
     moc
    -0.06
    usal
    -0.06
     shelf
    -0.06
    کن
    -0.06
     stern
    -0.06
    POSITIVE LOGITS
    %.↵↵
    0.07
    /{}/
    0.07
    .Next
    0.06
    -bootstrap
    0.06
    .`|`↵
    0.06
    iture
    0.06
    """),↵
    0.06
    liament
    0.06
    айте
    0.06
    )object
    0.06
    Act Density 0.590%

    No Known Activations