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

    Neuronpedia

    INDEX
    Explanations

    non-English language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CLUDING
    -0.08
     обеспе
    -0.07
     Nearby
    -0.07
    ोकर
    -0.07
    imiters
    -0.07
     achievable
    -0.06
     strangers
    -0.06
    Invoker
    -0.06
     vyrá
    -0.06
    isplay
    -0.06
    POSITIVE LOGITS
    Pas
    0.07
    MOTE
    0.06
    ,path
    0.06
    _MAX
    0.06
    รถ
    0.06
     charisma
    0.06
     adel
    0.06
    ,label
    0.06
    lava
    0.06
    ís
    0.06
    Act Density 0.037%

    No Known Activations