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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thomas
    -0.07
     Kang
    -0.07
    dap
    -0.06
    ’nde
    -0.06
    gres
    -0.06
    اث
    -0.06
     Rust
    -0.06
    _Output
    -0.06
    ond
    -0.06
     놀
    -0.06
    POSITIVE LOGITS
     incr
    0.07
    无
    0.07
    عار
    0.06
     lab
    0.06
          
    0.06
     advis
    0.06
     θέ
    0.06
     mn
    0.06
     "~
    0.06
     inv
    0.06
    Act Density 0.024%

    No Known Activations