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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spheres
    -0.07
    紅
    -0.07
    微笑
    -0.06
     once
    -0.06
    Resistance
    -0.06
    、な
    -0.06
     ora
    -0.06
     beforehand
    -0.06
     üç
    -0.06
    natural
    -0.06
    POSITIVE LOGITS
     mutate
    0.06
    getIndex
    0.06
    	glut
    0.06
    rasing
    0.06
    ربی
    0.06
    ustrial
    0.06
    .addTarget
    0.06
    books
    0.06
    .paginator
    0.06
    -redux
    0.06
    Act Density 0.143%

    No Known Activations