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

    Neuronpedia

    INDEX
    Explanations

    away

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maison
    -0.07
    obox
    -0.07
     Pale
    -0.06
     mer
    -0.06
     wells
    -0.06
     Springs
    -0.06
    Incoming
    -0.06
    ensity
    -0.06
     Chennai
    -0.06
     Quebec
    -0.06
    POSITIVE LOGITS
    Expr
    0.08
    .UserName
    0.06
    bellion
    0.06
    ンパ
    0.06
     neu
    0.06
     Majority
    0.06
    acios
    0.06
     خارج
    0.06
    Balance
    0.06
     recoil
    0.06
    Act Density 0.000%

    No Known Activations