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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burg
    -0.07
    Sql
    -0.07
     Вер
    -0.06
    واء
    -0.06
     wartime
    -0.06
    example
    -0.06
    ്�
    -0.06
    Ctrls
    -0.06
    डर
    -0.06
    经
    -0.06
    POSITIVE LOGITS
    +t
    0.07
     tidy
    0.06
    _tensor
    0.06
    onden
    0.06
    prep
    0.06
     embarrassed
    0.06
     </
    0.06
     playa
    0.06
    rels
    0.06
     implant
    0.06
    Act Density 0.000%

    No Known Activations