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

    Neuronpedia

    INDEX
    Explanations

    introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🍌
    -0.08
     Pai
    -0.07
     confined
    -0.07
     shampoo
    -0.06
     pertaining
    -0.06
     absentee
    -0.06
     준비
    -0.06
    蔀
    -0.06
    刘某
    -0.06
    .translate
    -0.06
    POSITIVE LOGITS
    WAIT
    0.07
    sequence
    0.07
    -Methods
    0.07
    Hz
    0.07
    经济技术
    0.07
    notice
    0.07
    .accessToken
    0.07
    .navigator
    0.07
    league
    0.07
    sky
    0.07
    Act Density 0.001%

    No Known Activations