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

    Neuronpedia

    INDEX
    Explanations

    code references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clit
    -0.06
    7
    -0.06
    DOM
    -0.06
     Rue
    -0.06
     bravery
    -0.06
     metaphor
    -0.06
    	Il
    -0.06
    Beautiful
    -0.06
     gram
    -0.06
    _DB
    -0.06
    POSITIVE LOGITS
    -delay
    0.07
    ">&
    0.07
    activ
    0.06
     Margin
    0.06
    Expires
    0.06
     많은
    0.06
    datepicker
    0.06
     亚洲
    0.06
    .libs
    0.06
     surpass
    0.06
    Act Density 0.442%

    No Known Activations