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

    Neuronpedia

    INDEX
    Explanations

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Very
    -0.78
     very
    -0.66
    very
    -0.66
     Lighter
    -0.64
     destul
    -0.64
     quelquefois
    -0.63
     préféré
    -0.63
     coarser
    -0.60
     BorderSide
    -0.59
     Very
    -0.58
    POSITIVE LOGITS
    曖昧さ回避
    0.68
    #+#
    0.67
    esgue
    0.60
     Yates
    0.51
    numerusform
    0.51
    úgó
    0.51
    CCER
    0.50
     lateinit
    0.50
    zumaki
    0.50
    CROSSTALK
    0.49
    Act Density 0.067%

    No Known Activations