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
    .Settings
    -0.07
    dismiss
    -0.07
     Become
    -0.07
     Firebase
    -0.07
     retrieval
    -0.07
     Pending
    -0.07
    Painter
    -0.07
     Hussein
    -0.07
     م
    -0.07
     Berlin
    -0.07
    POSITIVE LOGITS
    omencl
    0.08
    л
    0.07
           
    0.07
     '\''
    0.07
       
    0.07
    컴
    0.07
     bzw
    0.07
    𝐋
    0.07
    ]+'
    0.07
    老鼠
    0.07
    Act Density 0.004%

    No Known Activations