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

    Neuronpedia

    INDEX
    Explanations

    supporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edir
    -0.07
     Beach
    -0.07
    .new
    -0.07
     allocated
    -0.06
     paradise
    -0.06
     béné
    -0.06
     forecast
    -0.06
     Clearance
    -0.06
    _frm
    -0.06
     dés
    -0.06
    POSITIVE LOGITS
     supporting
    0.09
    音楽
    0.07
     QtCore
    0.07
     windy
    0.06
     classy
    0.06
    -proxy
    0.06
    span
    0.06
     병
    0.06
     알
    0.06
     �
    0.06
    Act Density 0.005%

    No Known Activations