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

    Neuronpedia

    INDEX
    Explanations

    reduced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rec
    -0.07
     grains
    -0.07
     byly
    -0.07
    oload
    -0.07
    ANTED
    -0.06
    _pay
    -0.06
     particle
    -0.06
    nas
    -0.06
    _scenario
    -0.06
    macro
    -0.06
    POSITIVE LOGITS
     checkpoints
    0.07
    igail
    0.06
    .CONT
    0.06
     своєї
    0.06
    _CNTL
    0.06
    �
    0.06
    CONT
    0.06
     Katrina
    0.06
     اینتر
    0.06
    roducing
    0.06
    Act Density 0.062%

    No Known Activations