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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .startswith
    -0.08
     chief
    -0.07
     Ben
    -0.07
    chen
    -0.07
     איפה
    -0.07
    폴
    -0.07
    쟤
    -0.06
     guy
    -0.06
     culprit
    -0.06
     부분
    -0.06
    POSITIVE LOGITS
    PointerType
    0.07
     sessions
    0.07
    egment
    0.07
     biscuits
    0.07
     hikes
    0.07
    纪录片
    0.07
    ournée
    0.06
    ivals
    0.06
    ust
    0.06
    ToDevice
    0.06
    Act Density 0.004%

    No Known Activations