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

    Neuronpedia

    INDEX
    Explanations

    Dennis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igg
    -0.08
     Evans
    -0.07
    -big
    -0.07
    가는
    -0.07
     complication
    -0.07
    称为
    -0.07
    .authenticate
    -0.07
    Eight
    -0.07
     flock
    -0.07
    ely
    -0.07
    POSITIVE LOGITS
    𝐔
    0.07
    たち
    0.07
    ˣ
    0.07
    נחל
    0.07
    (program
    0.06
    (TABLE
    0.06
     görül
    0.06
     {/*
    0.06
    Uri
    0.06
     Ramadan
    0.06
    Act Density 0.178%

    No Known Activations