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

    Neuronpedia

    INDEX
    Explanations

    "Will" or "Can"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     remembering
    -0.06
    PackageManager
    -0.06
     remembers
    -0.06
    obierno
    -0.06
    Kate
    -0.06
     scramble
    -0.06
    <>
    -0.06
     remember
    -0.06
    apellido
    -0.06
    POSITIVE LOGITS
    oubtedly
    0.07
    ництво
    0.06
    FU
    0.06
     lining
    0.06
     대구
    0.06
     diplom
    0.06
    .variable
    0.06
    lex
    0.06
    _str
    0.06
    vel
    0.06
    Act Density 0.039%

    No Known Activations