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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cast
    -0.07
     تكييف
    -0.07
    _offer
    -0.07
    ॉक
    -0.07
     �
    -0.06
     tav
    -0.06
     демон
    -0.06
     Puppet
    -0.06
     uygulam
    -0.06
    amage
    -0.06
    POSITIVE LOGITS
     shitty
    0.07
    .keys
    0.06
     clinical
    0.06
    .getResources
    0.06
    )،
    0.06
     technical
    0.06
    Vertical
    0.06
    ��
    0.06
     trình
    0.06
     россий
    0.06
    Act Density 0.010%

    No Known Activations