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

    Neuronpedia

    INDEX
    Explanations

    placeholders and templates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bus
    -0.08
     orthodox
    -0.08
    orton
    -0.08
     Nih
    -0.07
     bus
    -0.07
    _DIS
    -0.07
     turi
    -0.07
     oks
    -0.07
     ldc
    -0.07
     pursued
    -0.07
    POSITIVE LOGITS
     placeholders
    0.15
     placeholder
    0.11
    .placeholder
    0.11
     шаб
    0.11
     Template
    0.10
    模板
    0.10
    Template
    0.10
     adjustable
    0.10
     Editable
    0.10
     adaptable
    0.10
    Act Density 0.024%

    No Known Activations