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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atchewan
    -0.07
    .generated
    -0.06
     averaged
    -0.06
    ouse
    -0.06
    ervers
    -0.06
     regularly
    -0.06
     squadron
    -0.06
    728
    -0.06
    _ptr
    -0.06
     former
    -0.06
    POSITIVE LOGITS
    APT
    0.06
    employed
    0.06
    Too
    0.06
    udiantes
    0.06
     Cookies
    0.06
    mentor
    0.06
    planation
    0.06
    .Children
    0.06
     ail
    0.06
     atención
    0.06
    Act Density 0.021%

    No Known Activations