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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ｄ
    -0.07
    urrenc
    -0.07
    hap
    -0.06
    _qual
    -0.06
    reements
    -0.06
     Deletes
    -0.06
    ombie
    -0.06
     traumat
    -0.06
    remain
    -0.06
    privation
    -0.06
    POSITIVE LOGITS
    Target
    0.08
     استر
    0.06
    两人
    0.06
    /github
    0.06
     }()↵
    0.06
    hands
    0.06
    Insp
    0.06
    .collection
    0.06
     createStore
    0.06
    .cpp
    0.06
    Act Density 0.000%

    No Known Activations