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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Tree
    -0.07
    имер
    -0.07
    iteit
    -0.07
    .text
    -0.07
    ==============↵
    -0.06
    ará
    -0.06
    .,
    -0.06
    Warn
    -0.06
    _request
    -0.06
    	set
    -0.06
    POSITIVE LOGITS
     side
    0.07
    ention
    0.07
    <translation
    0.06
     subtle
    0.06
    spiel
    0.06
     deprived
    0.06
    micro
    0.06
     pl
    0.06
    blo
    0.06
    Û
    0.06
    Act Density 0.009%

    No Known Activations