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

    Neuronpedia

    INDEX
    Explanations

    strategy building games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gro
    -0.07
    weg
    -0.07
    ked
    -0.07
     sha
    -0.07
    ��
    -0.07
     yoksa
    -0.06
    för
    -0.06
     яку
    -0.06
     lần
    -0.06
    市
    -0.06
    POSITIVE LOGITS
    ]bool
    0.07
    .ToList
    0.06
     scape
    0.06
     jsonObj
    0.06
    .port
    0.06
    161
    0.06
     وغير
    0.06
    AllWindows
    0.06
    _keep
    0.06
    _OPT
    0.06
    Act Density 0.031%

    No Known Activations