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

    Neuronpedia

    INDEX
    Explanations

    internet search

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tek
    -0.07
    updates
    -0.07
    pref
    -0.06
     імен
    -0.06
    第
    -0.06
    \views
    -0.06
     Malta
    -0.06
    泊
    -0.06
    官
    -0.06
    番
    -0.06
    POSITIVE LOGITS
    .weapon
    0.07
    .Multiline
    0.06
     adulti
    0.06
    ",$
    0.06
     поє
    0.06
     prostitute
    0.06
     archived
    0.06
    	add
    0.06
     passport
    0.06
     Dire
    0.06
    Act Density 0.063%

    No Known Activations