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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Instances
    -0.06
     faster
    -0.06
    Emitter
    -0.06
    asting
    -0.06
     =================================================
    -0.06
    nect
    -0.06
    Nodes
    -0.06
    publisher
    -0.06
    -store
    -0.06
    (a
    -0.06
    POSITIVE LOGITS
     podrob
    0.07
     су
    0.07
    ipzig
    0.07
     Mathematics
    0.07
     ترب
    0.07
    	cout
    0.07
     CFG
    0.06
     MCP
    0.06
    GLfloat
    0.06
     İn
    0.06
    Act Density 0.012%

    No Known Activations