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

    Neuronpedia

    INDEX
    Explanations

    Code/Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    堽
    -0.08
    _inventory
    -0.07
    cooldown
    -0.07
    .GridView
    -0.07
    APolynomial
    -0.07
     enlight
    -0.07
    أشياء
    -0.07
    tableView
    -0.07
     graveyard
    -0.07
    少量
    -0.07
    POSITIVE LOGITS
    
↵

↵
    0.08
     уси
    0.08
    截图
    0.07
    武术
    0.07
    clipboard
    0.07
    >

↵
    0.07
     Picture
    0.06
    �
    0.06
    _filt
    0.06
    𝐁
    0.06
    Act Density 0.197%

    No Known Activations