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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     signings
    -0.06
    _php
    -0.06
     Buk
    -0.06
    ようです
    -0.06
    AIR
    -0.06
     işç
    -0.06
    .OK
    -0.06
    +k
    -0.06
    ublisher
    -0.06
    ி
    -0.06
    POSITIVE LOGITS
    (href
    0.07
     lips
    0.07
     вост
    0.06
    bestos
    0.06
     Titles
    0.06
     Gloria
    0.06
     oxygen
    0.06
     dred
    0.06
    Filename
    0.06
    .removeEventListener
    0.06
    Act Density 0.018%

    No Known Activations