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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    י�
    -0.07
     TextView
    -0.06
     gravitational
    -0.06
     Ed
    -0.06
    UCKET
    -0.06
    PWD
    -0.06
    Bin
    -0.06
    .FileNotFoundException
    -0.06
    /****************************************************************************
    -0.06
    !';↵
    -0.06
    POSITIVE LOGITS
    Stores
    0.07
     lớ
    0.06
    (actor
    0.06
    agate
    0.06
     broth
    0.06
    songs
    0.06
    лав
    0.06
    ลา
    0.06
    dato
    0.06
    律
    0.06
    Act Density 0.000%

    No Known Activations