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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    азв
    -0.07
     elders
    -0.07
    -success
    -0.07
     Corey
    -0.06
     RAW
    -0.06
    /signup
    -0.06
    /save
    -0.06
    แดง
    -0.06
     gerektir
    -0.06
    _bad
    -0.06
    POSITIVE LOGITS
     kosher
    0.07
     dialogRef
    0.06
    attachments
    0.06
     [];
    0.06
     knowledgeable
    0.06
    .TextAlignment
    0.06
     διά
    0.06
     말씀
    0.06
     irrit
    0.06
    ِّ
    0.06
    Act Density 0.310%

    No Known Activations