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

    Neuronpedia

    INDEX
    Explanations

    neglig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purity
    -0.06
     cannot
    -0.06
     Archbishop
    -0.06
    ?;↵
    -0.06
    -free
    -0.05
     stones
    -0.05
     boosting
    -0.05
    <Test
    -0.05
    Ra
    -0.05
    -0.05
    POSITIVE LOGITS
     negligent
    0.08
    ilst
    0.08
    けれど
    0.07
     Thiết
    0.07
     Snapchat
    0.07
    nez
    0.07
     Linkedin
    0.07
    امل
    0.07
     Ihren
    0.07
    istrate
    0.07
    Act Density 0.003%

    No Known Activations