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

    Neuronpedia

    INDEX
    Explanations

    Various forms of writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     describe
    -0.07
    multiline
    -0.06
     great
    -0.06
     facts
    -0.06
     findings
    -0.06
    ARRIER
    -0.06
     Allocator
    -0.06
     verify
    -0.06
     Registers
    -0.06
     Fabric
    -0.06
    POSITIVE LOGITS
     побед
    0.07
    _highlight
    0.06
    웃
    0.06
    _ATOMIC
    0.06
    سة
    0.06
     attend
    0.06
    FromString
    0.06
    浪
    0.06
    marshall
    0.06
    assessment
    0.06
    Act Density 0.017%

    No Known Activations