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

    Neuronpedia

    INDEX
    Explanations

    non-English code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ůr
    -0.07
    913
    -0.06
    .second
    -0.06
    ющими
    -0.06
     Menschen
    -0.06
     respects
    -0.06
     grunt
    -0.06
    旁
    -0.06
     Wohnung
    -0.06
    	tree
    -0.06
    POSITIVE LOGITS
    _SELECTED
    0.07
     tackles
    0.07
    Availability
    0.07
    σκε
    0.07
     Huffington
    0.06
    _ATTACHMENT
    0.06
     termination
    0.06
     SNP
    0.06
    คโน
    0.06
     INFO
    0.06
    Act Density 0.198%

    No Known Activations