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

    Neuronpedia

    INDEX
    Explanations

    STR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    	↵	↵	↵	↵
    -0.07
    -san
    -0.06
     jot
    -0.06
    Ö
    -0.06
     woo
    -0.06
     plum
    -0.06
    Ê
    -0.06
     properly
    -0.06
    -be
    -0.06
    POSITIVE LOGITS
    interopRequireDefault
    0.11
    駅徒歩
    0.06
    suz
    0.06
     Clifford
    0.06
    irectory
    0.06
    Naming
    0.06
    ichtet
    0.06
    ateur
    0.06
    (fout
    0.06
    /--
    0.06
    Act Density 0.000%

    No Known Activations