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
     TTC
    -0.07
    AttributedString
    -0.06
     que
    -0.06
    OLT
    -0.06
    .Geometry
    -0.06
     Dod
    -0.06
     Stanford
    -0.06
    亡
    -0.06
    /{{
    -0.06
    ahrung
    -0.06
    POSITIVE LOGITS
     handles
    0.06
     действия
    0.06
    entiful
    0.06
    действ
    0.06
     BAR
    0.06
    ohn
    0.06
     sinc
    0.06
     demands
    0.06
    ünde
    0.06
     时间
    0.06
    Act Density 0.032%

    No Known Activations