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

    Neuronpedia

    INDEX
    Explanations

    Conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pulls
    -0.07
     ACTION
    -0.06
    IELDS
    -0.06
    (Equal
    -0.06
    (Packet
    -0.06
    ometr
    -0.06
     hotels
    -0.06
    imar
    -0.06
     Processor
    -0.06
     Payload
    -0.06
    POSITIVE LOGITS
     biom
    0.07
    kin
    0.06
    ouver
    0.06
    adr
    0.06
    username
    0.06
     indeb
    0.06
    ]]></
    0.06
    动生成
    0.06
     ngôn
    0.06
     teaser
    0.06
    Act Density 0.199%

    No Known Activations