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

    Neuronpedia

    INDEX
    Explanations

    often

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸įåħģ许
    -0.29
    éĽĨåĽ¢èĤ¡ä»½
    -0.28
    éĩī
    -0.27
    çĭ¬
    -0.27
     occ
    -0.25
    ilename
    -0.25
     Realty
    -0.25
    yard
    -0.24
    iteur
    -0.24
    æ¯ı次éĥ½
    -0.24
    POSITIVE LOGITS
    dap
    0.27
    çĶ±ä¸ŃåĽ½
    0.26
    аÑĨион
    0.25
    å®ļäºĨ
    0.25
    cop
    0.25
     dap
    0.24
     Harm
    0.24
     kop
    0.24
     Schl
    0.24
    erp
    0.23
    Act Density 0.023%

    No Known Activations