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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jail
    -0.07
    .getFirst
    -0.06
     If
    -0.06
     concerned
    -0.06
    _UNITS
    -0.06
    Firestore
    -0.06
     walk
    -0.06
     blown
    -0.06
     debt
    -0.06
     promo
    -0.06
    POSITIVE LOGITS
    _DIPSETTING
    0.08
     Operand
    0.07
    .strategy
    0.06
     habil
    0.06
    angep
    0.06
    kte
    0.06
     визнач
    0.06
     клад
    0.06
     Creat
    0.06
    Detach
    0.06
    Act Density 0.065%

    No Known Activations