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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frames
    -0.07
    apses
    -0.06
    /banner
    -0.06
     abundance
    -0.06
    ίν
    -0.06
     explanations
    -0.06
     fronts
    -0.06
    (vals
    -0.06
     misinformation
    -0.06
     cooperating
    -0.06
    POSITIVE LOGITS
     створю
    0.06
     sidewalks
    0.06
    キャ
    0.06
     Frances
    0.06
     abl
    0.06
    .getY
    0.06
     hasattr
    0.06
     kenn
    0.06
    부터
    0.05
    postData
    0.05
    Act Density 0.004%

    No Known Activations