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

    Neuronpedia

    INDEX
    Explanations

    fuel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pillar
    -0.07
    :{
    -0.06
    _TH
    -0.06
    except
    -0.06
    .condition
    -0.06
     clause
    -0.06
     SVC
    -0.06
     letters
    -0.06
    Unfortunately
    -0.06
     disagreements
    -0.06
    POSITIVE LOGITS
     confined
    0.06
    웅
    0.06
     vastly
    0.06
     Farrell
    0.06
    Lou
    0.06
     boycott
    0.06
    .jetbrains
    0.06
    Snackbar
    0.06
     federally
    0.06
     Angry
    0.06
    Act Density 0.002%

    No Known Activations