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

    Neuronpedia

    INDEX
    Explanations

    legal references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aned
    -0.06
    Cre
    -0.06
     Мож
    -0.06
     brill
    -0.06
     mars
    -0.06
    登录
    -0.06
    ской
    -0.06
    .fr
    -0.06
    ській
    -0.06
    повід
    -0.06
    POSITIVE LOGITS
    Ế
    0.07
    _dropout
    0.06
     dateTime
    0.06
     medieval
    0.06
     radio
    0.06
     PRO
    0.06
     Duterte
    0.06
     Steph
    0.06
    getReference
    0.06
    约
    0.05
    Act Density 0.002%

    No Known Activations