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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    translation
    -0.07
    jun
    -0.07
     backyard
    -0.07
    prov
    -0.07
    istrat
    -0.06
     protobuf
    -0.06
    wild
    -0.06
    arat
    -0.06
     hier
    -0.06
     sizin
    -0.06
    POSITIVE LOGITS
     hormones
    0.07
     FN
    0.07
    LC
    0.07
    ,&
    0.07
     contro
    0.06
    .EventType
    0.06
    )&&
    0.06
    xee
    0.06
    cc
    0.06
     openssl
    0.06
    Act Density 0.004%

    No Known Activations