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

    Neuronpedia

    INDEX
    Explanations

    Errors and Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    undai
    -0.07
     ili
    -0.07
     kterého
    -0.07
     Backup
    -0.07
     Thousand
    -0.06
    ी.
    -0.06
    Newsletter
    -0.06
    DBus
    -0.06
    玄
    -0.06
     Normal
    -0.06
    POSITIVE LOGITS
     worthless
    0.07
     lep
    0.06
     카
    0.06
     appearing
    0.06
     spacecraft
    0.06
    .userName
    0.06
    -labelled
    0.06
     forthcoming
    0.06
    .ForEach
    0.06
     Prompt
    0.06
    Act Density 0.299%

    No Known Activations