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

    Neuronpedia

    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    question
    -0.07
    Patient
    -0.07
     구
    -0.07
     ремонт
    -0.06
    redirect
    -0.06
    olley
    -0.06
    arnation
    -0.06
    oleč
    -0.06
    Flag
    -0.06
    /remove
    -0.06
    POSITIVE LOGITS
    _ALIGNMENT
    0.07
    _logic
    0.07
    经过
    0.06
     weighs
    0.06
     ضد
    0.06
    ologically
    0.06
     ideological
    0.06
     orbits
    0.06
    .bmp
    0.06
    おり
    0.06
    Act Density 0.164%

    No Known Activations