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

    Neuronpedia

    INDEX
    Explanations

    say cart

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iable
    -0.07
    iness
    -0.07
     Engineers
    -0.07
     ports
    -0.07
    ")(
    -0.07
     OH
    -0.07
     undecided
    -0.07
    stories
    -0.07
    ino
    -0.06
    átor
    -0.06
    POSITIVE LOGITS
     TMZ
    0.06
    变化
    0.06
    .Controllers
    0.06
    惊
    0.06
    _slide
    0.06
    .opacity
    0.06
    UniformLocation
    0.06
     Valve
    0.06
     улуч
    0.05
    ��
    0.05
    Act Density 0.034%

    No Known Activations