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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кла
    -0.06
     dobře
    -0.06
    ui
    -0.06
    zej
    -0.06
     bb
    -0.06
    	obj
    -0.06
    .cbo
    -0.06
    -ball
    -0.06
    ��
    -0.06
    Clusters
    -0.05
    POSITIVE LOGITS
     sogar
    0.07
    .System
    0.07
     Lions
    0.07
    =w
    0.07
     essentials
    0.07
    ordin
    0.06
     ук
    0.06
     EVENT
    0.06
    >Password
    0.06
    σίας
    0.06
    Act Density 0.026%

    No Known Activations