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

    Neuronpedia

    INDEX
    Explanations

    hop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ebx
    -0.07
     zásad
    -0.07
     الأد
    -0.06
    K
    -0.06
    ्यम
    -0.06
    ither
    -0.06
    RESSED
    -0.06
     saber
    -0.06
    README
    -0.06
     quer
    -0.06
    POSITIVE LOGITS
     knocks
    0.07
    ело
    0.07
    Lights
    0.06
     große
    0.06
    Australia
    0.06
    large
    0.06
     participates
    0.06
    tul
    0.06
    tsx
    0.06
    žití
    0.06
    Act Density 0.004%

    No Known Activations