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

    Neuronpedia

    INDEX
    Explanations

    encryption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maximal
    -0.07
    ARB
    -0.07
    ��
    -0.07
     政
    -0.06
     start
    -0.06
     身
    -0.06
    ội
    -0.06
     nostalg
    -0.06
     rival
    -0.06
     Fluid
    -0.06
    POSITIVE LOGITS
     encryption
    0.31
     Encryption
    0.21
    Encryption
    0.13
    encryption
    0.11
    ryption
    0.08
     Scroll
    0.07
     asoci
    0.06
    ック
    0.06
    Mor
    0.06
    .disable
    0.06
    Act Density 0.003%

    No Known Activations