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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LoadIdentity
    -0.08
     Circus
    -0.07
    íf
    -0.07
    unde
    -0.07
    Html
    -0.07
    DockControl
    -0.07
    압
    -0.07
    \uC
    -0.07
    λλ
    -0.06
    _DB
    -0.06
    POSITIVE LOGITS
     Tarif
    0.07
     existential
    0.07
     oraz
    0.06
    -linear
    0.06
     exploited
    0.06
     elderly
    0.06
     Additionally
    0.06
     cartesian
    0.06
     ขนาด
    0.06
     charisma
    0.06
    Act Density 0.001%

    No Known Activations