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

    Neuronpedia

    INDEX
    Explanations

    tail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gifts
    -0.07
     Walking
    -0.07
     Valerie
    -0.07
     pomoci
    -0.07
    OLUTION
    -0.07
    |,↵
    -0.07
    ί
    -0.06
    “If
    -0.06
    ート
    -0.06
     Putting
    -0.06
    POSITIVE LOGITS
    employer
    0.06
    })();
    0.06
     tail
    0.06
    taxonomy
    0.06
    ungle
    0.06
    opause
    0.06
    Subset
    0.06
     malformed
    0.06
     Tail
    0.06
    iever
    0.05
    Act Density 0.005%

    No Known Activations