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

    Neuronpedia

    INDEX
    Explanations

    social events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (r
    -0.07
    =r
    -0.06
    Born
    -0.06
    ，存于
    -0.06
     visceral
    -0.06
    &);↵
    -0.06
     человека
    -0.06
     directories
    -0.06
    slide
    -0.06
     filled
    -0.06
    POSITIVE LOGITS
    нием
    0.07
    idle
    0.07
    Neither
    0.06
     obscured
    0.06
     Postal
    0.06
     discret
    0.06
    /browser
    0.06
    APH
    0.06
    BTTagCompound
    0.06
     exaggerated
    0.06
    Act Density 0.014%

    No Known Activations