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

    Neuronpedia

    INDEX
    Explanations

    Solving equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ratios
    -0.08
    tos
    -0.08
     التخ
    -0.08
     emph
    -0.07
    يت
    -0.07
    .toolbar
    -0.07
    最
    -0.07
     rib
    -0.07
     stok
    -0.07
    Sender
    -0.07
    POSITIVE LOGITS
    Solutions
    0.12
     duplicates
    0.12
     Solutions
    0.11
    Duplicates
    0.11
    Multiplicity
    0.11
    solutions
    0.10
    duplicates
    0.10
     crossings
    0.10
     solutions
    0.10
     soluções
    0.10
    Act Density 0.060%

    No Known Activations