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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BX
    -0.07
     Gates
    -0.06
    _ro
    -0.06
     yaptığ
    -0.06
     Commons
    -0.06
     Injector
    -0.06
    ену
    -0.06
    :P
    -0.06
    �
    -0.06
     bene
    -0.06
    POSITIVE LOGITS
     getDefault
    0.07
    ImGui
    0.07
    .embedding
    0.06
    こんにちは
    0.06
    /sdk
    0.06
    	flash
    0.06
    Ljava
    0.06
    BYTES
    0.06
    ibBundleOrNil
    0.06
     görüntü
    0.06
    Act Density 0.020%

    No Known Activations