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

    Neuronpedia

    INDEX
    Explanations

    studied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ishing
    -0.07
     nk
    -0.07
     exagger
    -0.07
    小时候
    -0.07
    ictureBox
    -0.07
     Sor
    -0.07
    ิด
    -0.07
    吸附
    -0.06
     allocation
    -0.06
     제
    -0.06
    POSITIVE LOGITS
    dae
    0.07
    FAST
    0.06
    Woman
    0.06
    ughter
    0.06
    ровер
    0.06
     You
    0.06
    㫪
    0.06
     לחלוט
    0.06
    本金
    0.06
    )!
    0.06
    Act Density 0.040%

    No Known Activations