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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .btnCancel
    -0.07
    hb
    -0.06
    vat
    -0.06
     cant
    -0.06
    /runtime
    -0.06
    raně
    -0.06
     week
    -0.06
    िवर
    -0.06
     patio
    -0.06
    tin
    -0.05
    POSITIVE LOGITS
     Lines
    0.07
     pleasure
    0.07
     eased
    0.07
    ضل
    0.07
    unctuation
    0.07
    ishing
    0.06
    insics
    0.06
     arcs
    0.06
     mh
    0.06
     lines
    0.06
    Act Density 0.010%

    No Known Activations