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

    Neuronpedia

    INDEX
    Explanations

    element

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ruiz
    -0.07
    collision
    -0.07
     Ni
    -0.07
     vou
    -0.07
     newNode
    -0.06
     ăn
    -0.06
    ρευ
    -0.06
    _alias
    -0.06
    anguages
    -0.06
     Mej
    -0.06
    POSITIVE LOGITS
    ;';↵
    0.06
    PCS
    0.06
    elaide
    0.06
    qs
    0.06
     Vác
    0.06
    вою
    0.06
     firsthand
    0.06
    sett
    0.05
    注
    0.05
    Trip
    0.05
    Act Density 0.015%

    No Known Activations