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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -scrollbar
    -0.07
    _room
    -0.07
    ibration
    -0.07
    يار
    -0.06
     nk
    -0.06
     اینچ
    -0.06
    ٌ
    -0.06
     Comp
    -0.06
     specialties
    -0.06
    noloj
    -0.06
    POSITIVE LOGITS
     invites
    0.07
    BOOLE
    0.07
    layın
    0.06
    ZF
    0.06
     granddaughter
    0.06
     фун
    0.06
    可
    0.06
    909
    0.06
    WARD
    0.06
    incerely
    0.06
    Act Density 0.004%

    No Known Activations