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

    Neuronpedia

    INDEX
    Explanations

    Proportions and quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     searchString
    -0.07
    �
    -0.07
    stagram
    -0.06
     mockery
    -0.06
    ��
    -0.06
     misinformation
    -0.06
    conds
    -0.06
    恋
    -0.06
    kk
    -0.06
    .bc
    -0.06
    POSITIVE LOGITS
    ,filename
    0.08
     associations
    0.06
     depressive
    0.06
     Spin
    0.06
    	Create
    0.06
     instantiate
    0.06
     BIT
    0.06
    ierarchy
    0.06
     stalk
    0.06
     declared
    0.06
    Act Density 0.064%

    No Known Activations