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

    Neuronpedia

    INDEX
    Explanations

    citations and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lash
    -0.30
    andr
    -0.25
    |.↵
    -0.25
     verbally
    -0.25
    à¸Ħรà¸Ńà¸ļ
    -0.24
    lassen
    -0.24
    >(()
    -0.24
    ::__
    -0.23
    ackages
    -0.23
    utta
    -0.23
    POSITIVE LOGITS
    å¾Ĥ
    0.26
     phoenix
    0.26
    ç¥ĩ
    0.25
    åĢĮ
    0.25
    \Application
    0.25
     essential
    0.25
    åħ¬çĽĬæĢ§
    0.24
     mx
    0.24
    è°Ĵ
    0.24
    wives
    0.24
    Act Density 0.011%

    No Known Activations