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

    Neuronpedia

    INDEX
    Explanations

    hosts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :max
    -0.07
     MAX
    -0.07
    PREFIX
    -0.07
    aseña
    -0.07
     wiel
    -0.07
     accounted
    -0.07
    รค
    -0.06
     П
    -0.06
     merak
    -0.06
    .,
    -0.06
    POSITIVE LOGITS
    vision
    0.06
    ayar
    0.06
     Wir
    0.06
    /connection
    0.06
     duplic
    0.06
    _NPC
    0.06
    سی
    0.05
    adığı
    0.05
     date
    0.05
     Dod
    0.05
    Act Density 0.005%

    No Known Activations