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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OSC
    -0.07
     unfolds
    -0.07
    .attrs
    -0.06
     Cannes
    -0.06
     wedding
    -0.06
     Recruitment
    -0.06
     Под
    -0.06
     newcomer
    -0.06
    slaught
    -0.06
    Compiled
    -0.06
    POSITIVE LOGITS
    .requires
    0.08
    ��
    0.07
    thag
    0.06
    (latitude
    0.06
    ersed
    0.06
    ToLower
    0.06
     lange
    0.06
    lıkları
    0.06
     cient
    0.06
     cultiv
    0.06
    Act Density 0.010%

    No Known Activations