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
    ้ง
    -0.07
    ◂
    -0.07
    ampilkan
    -0.07
     prem
    -0.07
    �
    -0.07
     gli
    -0.07
    .sam
    -0.07
    ｺ
    -0.07
    ainties
    -0.07
    -second
    -0.07
    POSITIVE LOGITS
     distributor
    0.07
     dismay
    0.07
    ("/",
    0.07
    の中に
    0.07
    columns
    0.07
     Forms
    0.07
    readcrumb
    0.07
    roads
    0.07
    אמצע
    0.06
     mentoring
    0.06
    Act Density 0.008%

    No Known Activations