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

    Neuronpedia

    INDEX
    Explanations

    far

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yasal
    -0.07
    女人
    -0.07
    edef
    -0.07
    chen
    -0.06
     XCT
    -0.06
     Rew
    -0.06
     Burnett
    -0.06
     tablespoon
    -0.06
     niece
    -0.06
     livestock
    -0.06
    POSITIVE LOGITS
    _delay
    0.08
     同
    0.07
    rocessing
    0.07
    ForResult
    0.07
    iosk
    0.07
    InitStruct
    0.06
    follow
    0.06
     dismissal
    0.06
     вак
    0.06
    _supported
    0.06
    Act Density 0.010%

    No Known Activations