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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    humidity
    -0.06
    /controllers
    -0.06
     NOTICE
    -0.06
     Mater
    -0.06
    Flutter
    -0.06
     messageType
    -0.06
     προσ
    -0.06
     subway
    -0.06
     allegiance
    -0.06
    Tomorrow
    -0.06
    POSITIVE LOGITS
     admitted
    0.07
     platform
    0.06
     brag
    0.06
     lu
    0.06
     bệnh
    0.06
    attrib
    0.06
    cerpt
    0.06
     meis
    0.06
    Old
    0.06
     knih
    0.06
    Act Density 0.007%

    No Known Activations