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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anggal
    -0.07
     Audit
    -0.06
     Dev
    -0.06
     poj
    -0.06
    unge
    -0.06
    ropical
    -0.06
    aters
    -0.06
    riding
    -0.06
     میلادی
    -0.06
    едж
    -0.06
    POSITIVE LOGITS
     Phương
    0.07
    _success
    0.06
    715
    0.06
    .pay
    0.06
     �
    0.06
     Sob
    0.06
    @register
    0.06
    >{{$
    0.06
     akadem
    0.06
    ша
    0.06
    Act Density 0.065%

    No Known Activations