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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يار
    -0.08
    /customer
    -0.07
    egral
    -0.07
    __(/*!
    -0.07
    uity
    -0.07
     drawing
    -0.07
    綜
    -0.07
    我が
    -0.07
    角色
    -0.07
    激励
    -0.06
    POSITIVE LOGITS
     readline
    0.07
     Backbone
    0.07
    ConnectionString
    0.07
     yelling
    0.06
    ॥
    0.06
    UNC
    0.06
     parentheses
    0.06
     urz
    0.06
    ᅪ
    0.06
    "=>
    0.06
    Act Density 0.005%

    No Known Activations