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

    Neuronpedia

    INDEX
    Explanations

    Squ

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [Y
    -0.07
     diffuse
    -0.06
     ce
    -0.06
     Patio
    -0.06
    .getBlock
    -0.06
    reiben
    -0.06
    )$_
    -0.06
     geben
    -0.06
     purification
    -0.06
     Compiler
    -0.06
    POSITIVE LOGITS
    _IMM
    0.08
    Hen
    0.07
    fusion
    0.07
     squ
    0.07
    stí
    0.07
     rental
    0.07
    DIS
    0.06
    ुओ
    0.06
     sph
    0.06
    Too
    0.06
    Act Density 0.006%

    No Known Activations