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

    Neuronpedia

    INDEX
    Explanations

    bathrooms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >>
    -0.06
     �
    -0.06
    lou
    -0.06
    ấm
    -0.06
    chedulers
    -0.06
    ulnerable
    -0.06
    Availability
    -0.06
     dirt
    -0.06
    уючи
    -0.06
     fact
    -0.06
    POSITIVE LOGITS
     vier
    0.07
     Priv
    0.07
     kanal
    0.07
    hift
    0.07
    蛇
    0.06
     truncated
    0.06
    .rect
    0.06
    lä
    0.06
     trat
    0.06
     Mei
    0.06
    Act Density 0.281%

    No Known Activations