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

    Neuronpedia

    INDEX
    Explanations

    the/a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Medicine
    -0.07
     thee
    -0.06
    doctor
    -0.06
    fidf
    -0.06
     pudding
    -0.06
     leaking
    -0.06
     controversy
    -0.06
    folk
    -0.06
    leasing
    -0.06
     presses
    -0.06
    POSITIVE LOGITS
     систему
    0.08
     }}"↵
    0.07
    _PLAY
    0.07
     pojist
    0.07
    caff
    0.07
     graphene
    0.07
     gef
    0.06
     实
    0.06
     dissolved
    0.06
    $core
    0.06
    Act Density 0.030%

    No Known Activations