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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >}</
    -0.07
    ัมพ
    -0.06
     Thy
    -0.06
    >".$
    -0.06
    複
    -0.06
    मर
    -0.06
    820
    -0.06
     отк
    -0.06
     Founded
    -0.06
    стру
    -0.06
    POSITIVE LOGITS
     proportions
    0.07
     levels
    0.07
     обыч
    0.07
     امنیت
    0.07
     rates
    0.06
     hardship
    0.06
     writable
    0.06
    quiet
    0.06
    ỗ
    0.06
    ISON
    0.06
    Act Density 0.008%

    No Known Activations