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

    Neuronpedia

    INDEX
    Explanations

    living a full life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mercy
    -0.07
    獲
    -0.06
    Roger
    -0.06
     米
    -0.06
     RCA
    -0.06
    ה
    -0.06
     Circus
    -0.06
        ↵    ↵
    -0.06
    ین
    -0.06
    話
    -0.06
    POSITIVE LOGITS
     hopefully
    0.07
    .hide
    0.07
    ersist
    0.06
    efault
    0.06
     Animator
    0.06
     Limited
    0.06
     normal
    0.06
    .getItem
    0.06
     unknown
    0.06
     subordinate
    0.06
    Act Density 0.031%

    No Known Activations