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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     momentos
    -0.07
     voj
    -0.07
    جان
    -0.06
    sob
    -0.06
    aad
    -0.06
     lecture
    -0.06
     ра
    -0.06
     logistics
    -0.06
    ër
    -0.06
     star
    -0.06
    POSITIVE LOGITS
    Semaphore
    0.07
    阿
    0.07
     =$
    0.06
    Backend
    0.06
     koruy
    0.06
     PCA
    0.06
     阿
    0.06
    जर
    0.06
     villagers
    0.06
    にある
    0.06
    Act Density 0.148%

    No Known Activations