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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theſe
    -0.92
     myſelf
    -0.92
     Efq
    -0.85
     Majefty
    -0.82
    NUMX
    -0.81
     ſeveral
    -0.80
     ſch
    -0.80
     Anſ
    -0.80
    <bos>
    -0.79
     Houſe
    -0.78
    POSITIVE LOGITS
    <eos>
    0.49
    OrEqualTo
    0.44
    OrEqual
    0.43
    ois
    0.42
    ALLED
    0.42
     auto
    0.42
    ↵↵↵
    0.42
     Put
    0.41
    ↵↵
    0.41
    Földrajzportál
    0.41
    Act Density 0.005%

    No Known Activations