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

    Neuronpedia

    INDEX
    Explanations

    Importance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    IDA
    -0.07
    obao
    -0.07
    idar
    -0.06
    Rich
    -0.06
    Lots
    -0.06
    Registers
    -0.06
    Live
    -0.06
    eax
    -0.06
    .minecraft
    -0.06
    POSITIVE LOGITS
     purity
    0.07
    antically
    0.06
     completamente
    0.06
     alm
    0.06
    �
    0.06
     '')
    0.06
     amat
    0.06
     більш
    0.06
    246
    0.06
     administered
    0.06
    Act Density 0.047%

    No Known Activations