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

    Neuronpedia

    INDEX
    Explanations

    eg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ु�
    -0.07
    -cli
    -0.06
     Loans
    -0.06
    .fromFunction
    -0.06
    _spin
    -0.06
     frau
    -0.06
     Cd
    -0.06
    ールド
    -0.06
    	win
    -0.06
    γγραφ
    -0.06
    POSITIVE LOGITS
     tread
    0.07
    ьют
    0.07
    uly
    0.07
    ued
    0.06
     Mehmet
    0.06
    YLeaf
    0.06
    ETHER
    0.06
     take
    0.06
     RCA
    0.06
    ajar
    0.06
    Act Density 0.015%

    No Known Activations