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

    Neuronpedia

    INDEX
    Explanations

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     save
    -0.07
    oward
    -0.07
    цит
    -0.06
    urpose
    -0.06
    γωγ
    -0.06
     Tic
    -0.06
    ulatory
    -0.06
    游
    -0.06
     Manson
    -0.06
     FIFA
    -0.06
    POSITIVE LOGITS
     sheriff
    0.06
     GENER
    0.06
    department
    0.06
    myModal
    0.06
    /controllers
    0.06
     IT
    0.06
     Plays
    0.06
     setattr
    0.06
    条件
    0.06
     Marks
    0.06
    Act Density 0.031%

    No Known Activations