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

    Neuronpedia

    INDEX
    Explanations

    properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indice
    -0.06
    Kal
    -0.06
    莱
    -0.06
    etes
    -0.06
    aily
    -0.06
    Cum
    -0.06
     gates
    -0.06
     vents
    -0.06
    ouncy
    -0.06
    ámara
    -0.06
    POSITIVE LOGITS
     comforts
    0.07
     groundwork
    0.07
    奴
    0.07
     Software
    0.07
     consolidation
    0.07
     Đặc
    0.07
    lášení
    0.07
     prostě
    0.07
     Leader
    0.06
    -describedby
    0.06
    Act Density 0.052%

    No Known Activations