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

    Neuronpedia

    INDEX
    Explanations

    supporting causes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DOT
    -0.07
     mænd
    -0.06
     hazır
    -0.06
    lid
    -0.06
    acomment
    -0.06
    ět
    -0.06
    -League
    -0.06
    íř
    -0.06
    .Configuration
    -0.06
    кового
    -0.06
    POSITIVE LOGITS
     sleep
    0.07
     dreams
    0.06
    _Cell
    0.06
    /response
    0.06
     resets
    0.06
     referral
    0.06
     Simmons
    0.06
    _alloc
    0.06
    _TestCase
    0.06
     confirmation
    0.06
    Act Density 0.009%

    No Known Activations