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

    Neuronpedia

    INDEX
    Explanations

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Har
    -0.07
    FileSystem
    -0.07
    -Bold
    -0.07
     Memories
    -0.07
    Magn
    -0.07
     TNT
    -0.07
    ICAST
    -0.06
    .admin
    -0.06
     Magn
    -0.06
     Gordon
    -0.06
    POSITIVE LOGITS
    lee
    0.07
    CKER
    0.06
     برگزار
    0.06
     cooperate
    0.06
     <>↵
    0.06
    álie
    0.06
    zung
    0.06
    [c
    0.06
    ��
    0.06
     suo
    0.06
    Act Density 0.005%

    No Known Activations