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

    Neuronpedia

    INDEX
    Explanations

    otes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الذين
    -0.07
     haunted
    -0.07
     declarations
    -0.07
    XP
    -0.07
    iture
    -0.06
     west
    -0.06
     iteration
    -0.06
     volts
    -0.06
    sand
    -0.06
     vf
    -0.06
    POSITIVE LOGITS
    -mails
    0.07
     Ens
    0.07
    Democratic
    0.07
    (manager
    0.06
    Inspector
    0.06
    !=-
    0.06
    Mrs
    0.06
    issippi
    0.06
    Higher
    0.06
     honoring
    0.06
    Act Density 0.000%

    No Known Activations