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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dispatch
    -0.07
    殊
    -0.06
     territorial
    -0.06
     Lights
    -0.06
     $('<
    -0.06
     lights
    -0.06
     exquisite
    -0.06
    _phy
    -0.06
     uomo
    -0.06
    -‐
    -0.06
    POSITIVE LOGITS
    pectives
    0.08
     buffers
    0.06
     collaborate
    0.06
     suppression
    0.06
     hike
    0.06
     Fif
    0.06
     Holocaust
    0.06
    rary
    0.06
     Applied
    0.06
    _SPEED
    0.06
    Act Density 0.004%

    No Known Activations