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
    aug
    -0.07
    uyền
    -0.06
     куда
    -0.06
     самый
    -0.06
     stringByAppending
    -0.06
     prefers
    -0.06
    implify
    -0.06
     Preconditions
    -0.06
     Name
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    svc
    0.07
    =label
    0.06
     lies
    0.06
     ale
    0.06
    위
    0.06
     музы
    0.06
     клу
    0.06
    524
    0.06
    .emit
    0.06
    (qu
    0.06
    Act Density 0.000%

    No Known Activations