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

    Neuronpedia

    INDEX
    Explanations

    California

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (the
    -0.07
    ließlich
    -0.07
     MCU
    -0.06
    MBProgressHUD
    -0.06
    Trip
    -0.06
     Muslims
    -0.06
    onde
    -0.06
     underwear
    -0.06
     Royal
    -0.06
    ε
    -0.06
    POSITIVE LOGITS
     energie
    0.07
     spos
    0.07
     Weak
    0.06
     Bootstrap
    0.06
     ui
    0.06
    没
    0.06
    cc
    0.06
     getColumn
    0.06
     yeah
    0.06
     作
    0.06
    Act Density 0.007%

    No Known Activations