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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Contacts
    -0.07
     UserManager
    -0.07
     περ
    -0.07
     brill
    -0.07
    ğiz
    -0.06
    .hex
    -0.06
     evaluated
    -0.06
    ắc
    -0.06
    덕
    -0.06
     wh
    -0.06
    POSITIVE LOGITS
     кос
    0.07
     quicker
    0.07
     fend
    0.07
     Kag
    0.06
     Even
    0.06
     stunt
    0.06
    .fasterxml
    0.06
     Smithsonian
    0.06
     CJ
    0.06
    ."','".$
    0.06
    Act Density 0.000%

    No Known Activations