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

    Neuronpedia

    INDEX
    Explanations

    grant funding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Myers
    -0.07
    ичного
    -0.07
     svě
    -0.07
     welt
    -0.06
    uell
    -0.06
    ock
    -0.06
    ُر
    -0.06
     mist
    -0.06
    hua
    -0.06
    -status
    -0.06
    POSITIVE LOGITS
    /lic
    0.07
    (Il
    0.06
    although
    0.06
     opting
    0.06
    獎
    0.06
    ับท
    0.06
     elected
    0.06
    .getCode
    0.06
    .lastname
    0.06
    (dynamic
    0.06
    Act Density 0.005%

    No Known Activations