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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Camera
    -0.07
     місце
    -0.07
     Dutch
    -0.07
     Unsafe
    -0.07
    AGIC
    -0.07
    oped
    -0.07
    quare
    -0.07
    کور
    -0.07
     captured
    -0.06
     زمین
    -0.06
    POSITIVE LOGITS
    <Post
    0.06
    �
    0.06
    -assets
    0.06
     contributes
    0.06
    न
    0.06
    .?
    0.06
    .Home
    0.06
     subscribed
    0.05
     requested
    0.05
    avirus
    0.05
    Act Density 0.010%

    No Known Activations