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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     writes
    -0.07
    getMock
    -0.07
    uentes
    -0.06
    >Title
    -0.06
     Leone
    -0.06
    :description
    -0.06
    implode
    -0.06
     becomes
    -0.06
     Get
    -0.06
    лючается
    -0.06
    POSITIVE LOGITS
    -piece
    0.08
     Dutch
    0.07
     samsung
    0.07
     amateur
    0.06
     음
    0.06
    buster
    0.06
     eye
    0.06
    ‍
    0.06
    TM
    0.06
     ValueType
    0.06
    Act Density 0.015%

    No Known Activations