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

    Neuronpedia

    INDEX
    Explanations

    recover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lacks
    -0.07
    [vertex
    -0.07
     Lib
    -0.07
     hiding
    -0.07
    一点儿
    -0.07
     بد
    -0.07
     Dick
    -0.06
    !="
    -0.06
     thăm
    -0.06
     hostname
    -0.06
    POSITIVE LOGITS
    loy
    0.07
    process
    0.07
    UPLOAD
    0.07
    𝓮
    0.07
    IENT
    0.07
     foreclosure
    0.07
    ội
    0.07
    workers
    0.07
     panels
    0.07
    ⤫
    0.06
    Act Density 0.001%

    No Known Activations