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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     origen
    -0.07
     sense
    -0.07
     witnessing
    -0.07
    -block
    -0.07
    disposed
    -0.07
    optim
    -0.06
    Block
    -0.06
     wei
    -0.06
    类型
    -0.06
    logged
    -0.06
    POSITIVE LOGITS
    illet
    0.06
     سرعت
    0.06
     araştırma
    0.06
     pulses
    0.06
     TTC
    0.06
     anticip
    0.06
     �
    0.06
     dhcp
    0.06
     Rosenberg
    0.05
     이동합니다
    0.05
    Act Density 0.022%

    No Known Activations