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

    Neuronpedia

    INDEX
    Explanations

    Alarms and detectors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intimacy
    -0.08
    fortune
    -0.08
     mencari
    -0.08
    fold
    -0.08
     innings
    -0.08
     Bills
    -0.08
     Spotify
    -0.07
     Fortune
    -0.07
     זוג
    -0.07
     batting
    -0.07
    POSITIVE LOGITS
    消防
    0.11
    救
    0.10
     evacu
    0.10
     OSHA
    0.09
     disposer
    0.09
     evacuation
    0.09
     secours
    0.09
     авар
    0.09
     FE
    0.09
     firef
    0.08
    Act Density 0.022%

    No Known Activations