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

    Neuronpedia

    INDEX
    Explanations

    focus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /project
    -0.07
     Erin
    -0.07
     اح
    -0.07
    metrical
    -0.07
    _pi
    -0.06
    .MM
    -0.06
    ("'"
    -0.06
    _UTIL
    -0.06
    وش
    -0.06
     EINVAL
    -0.06
    POSITIVE LOGITS
    ских
    0.07
     donate
    0.07
     grosse
    0.07
     ack
    0.07
     ”
    0.07
     wyn
    0.07
     qualification
    0.07
     www
    0.06
     hart
    0.06
    .Many
    0.06
    Act Density 0.005%

    No Known Activations