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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calcular
    -0.07
    량
    -0.07
     Manuals
    -0.06
     fwrite
    -0.06
    Former
    -0.06
    еві
    -0.06
     Premiere
    -0.06
     lame
    -0.06
     Modular
    -0.05
    antan
    -0.05
    POSITIVE LOGITS
    JAVA
    0.07
     wre
    0.07
     اند
    0.06
    verified
    0.06
     ong
    0.06
    _raise
    0.06
    ��
    0.06
    弹
    0.06
    нике
    0.06
     nem
    0.06
    Act Density 0.005%

    No Known Activations