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

    Neuronpedia

    INDEX
    Explanations

    Reaching maximum capacity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Symbol
    -0.07
     downstairs
    -0.06
    味
    -0.06
     relative
    -0.06
     spear
    -0.06
     subsequ
    -0.06
     건
    -0.06
    _RECE
    -0.06
     �
    -0.06
    riangle
    -0.06
    POSITIVE LOGITS
    ้ม
    0.07
    (summary
    0.06
     vä
    0.06
     Fairfax
    0.06
     trăm
    0.06
     '').
    0.06
    ンツ
    0.06
    RET
    0.06
     içindeki
    0.06
    Discovery
    0.06
    Act Density 0.021%

    No Known Activations