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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ";
    -0.07
    -0.07
    He
    -0.07
    "F
    -0.07
    "My
    -0.07
    -0.06
    "N
    -0.06
    "B
    -0.06
    -0.06
    doesn
    -0.06
    POSITIVE LOGITS
     didFinish
    0.07
     ail
    0.07
     Orchestra
    0.07
     newRow
    0.07
    adata
    0.07
    nergie
    0.06
     Frag
    0.06
    ablytyped
    0.06
     wondered
    0.06
     rin
    0.06
    Act Density 0.006%

    No Known Activations