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

    Neuronpedia

    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mil
    -0.07
    ��
    -0.07
     dyn
    -0.07
    ,get
    -0.06
    ubuntu
    -0.06
    /**/*.
    -0.06
     unge
    -0.06
     embassy
    -0.06
     потім
    -0.06
    Born
    -0.06
    POSITIVE LOGITS
    prefer
    0.06
    elerini
    0.06
    _shot
    0.06
    様
    0.06
     promises
    0.06
    _NT
    0.06
    Grad
    0.06
    ivě
    0.06
     diploma
    0.06
    řed
    0.06
    Act Density 0.002%

    No Known Activations