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

    Neuronpedia

    INDEX
    Explanations

    character patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेदन
    -0.07
    軍
    -0.06
     OSI
    -0.06
    training
    -0.06
    近
    -0.06
     blending
    -0.06
     ballo
    -0.06
    μερ
    -0.06
     몸을
    -0.06
    .addData
    -0.06
    POSITIVE LOGITS
     UserService
    0.07
    ständ
    0.06
     plus
    0.06
    	false
    0.06
    иш
    0.06
    $ret
    0.06
     Ré
    0.06
    委
    0.06
    ulary
    0.06
     fileList
    0.06
    Act Density 0.048%

    No Known Activations