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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ディ
    -0.07
    _corpus
    -0.07
     Eden
    -0.07
    อดภ
    -0.07
     江
    -0.06
     eerste
    -0.06
    _bp
    -0.06
    _hid
    -0.06
    泊
    -0.06
    _lift
    -0.06
    POSITIVE LOGITS
     distracted
    0.06
     SUR
    0.06
     IND
    0.06
    	LOG
    0.06
     Require
    0.06
    &&!
    0.06
     бит
    0.05
     ruce
    0.05
    :"",↵
    0.05
    TOR
    0.05
    Act Density 0.027%

    No Known Activations